<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (cshalizi)</title>
    <link>https://pinboard.in/u:cshalizi/public/</link>
    <description>recent bookmarks from cshalizi</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.70023?campaign=wolearlyview"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2310.20609"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2303.04871"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2209.08223#"/>
	<rdf:li rdf:resource="https://www.cambridge.org/core/elements/apples-to-apples/5F0CCD49D9528EEE5C9CA6C65DEFEAD0"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2003.04235"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2107.07489"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2107.11403"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2105.14364"/>
	<rdf:li rdf:resource="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-1/Optimal-change-point-detection-and-localization-in-sparse-dynamic-networks/10.1214/20-AOS1953.short"/>
	<rdf:li rdf:resource="https://www.tandfonline.com/doi/full/10.1080/10618600.2020.1844214"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1911.02741"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.09828"/>
	<rdf:li rdf:resource="https://journals.sagepub.com/doi/full/10.1177/0049124118769113"/>
	<rdf:li rdf:resource="https://journals.aps.org/pre/abstract/10.1103/PhysRevE.102.062301"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.12416"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.12290"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1903.11117"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.10079"/>
	<rdf:li rdf:resource="https://www.tandfonline.com/doi/full/10.1080/01621459.2020.1763803"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aoas/1593449335"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1597370670"/>
	<rdf:li rdf:resource="https://mitpress.mit.edu/books/changing-connectomes"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1812.00769"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1811.08763"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1901.08521"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.02301"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1710.02761"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aoas/1571277767"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1703.03862"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1908.03836"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.13253"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.13464"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1707.00833"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1701.00505"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1905.11249"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1905.10302"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1812.03090"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1904.07414"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1903.02129"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1904.03348"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1801.07351"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1809.02512"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1804.03665"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1711.02123"/>
	<rdf:li rdf:resource="http://www.journals.uchicago.edu/doi/10.1086/597791"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1311.6425"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1202.1561"/>
	<rdf:li rdf:resource="http://papers.nips.cc/paper/3294-modeling-homophily-and-stochastic-equivalence-in-symmetric-relational-data"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1511.02976"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1602.01130"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1507.08376"/>
	<rdf:li rdf:resource="https://www.cs.purdue.edu/homes/neville/papers/moreno-icdm2013.pdf"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1506.08826"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1506.00669"/>
	<rdf:li rdf:resource="http://www.ncbi.nlm.nih.gov/pubmed/22008374"/>
	<rdf:li rdf:resource="http://www.pnas.org/content/112/10/2942.abstract.html"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1502.07576"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1409.2344"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1409.4317"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1405.3133"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1407.5525"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1411.1350"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1411.1437"/>
	<rdf:li rdf:resource="http://www.mitpressjournals.org/doi/abs/10.1162/NECO_a_00690"/>
	<rdf:li rdf:resource="http://www.pnas.org/content/111/49/E5321.abstract.html?etoc"/>
	<rdf:li rdf:resource="http://www.pnas.org/content/111/46/E4997.abstract.html?etoc"/>
	<rdf:li rdf:resource="http://www.ms.unimelb.edu.au/~aurored/delaigle-hall-hc4.pdf"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/math/0410072"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1001.0591"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.70023?campaign=wolearlyview">
    <title>Online Network Change Point Detection With Missing Values and Temporal Dependence - Xu - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2025-10-25T20:04:01+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.70023?campaign=wolearlyview</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, we study online change point detection in dynamic networks with time-heterogeneous missing patterns within networks and dependence across both nodes and time. The missingness probabilities, the entrywise sparsity of networks, the rank of networks and the jump size in terms of the Frobenius norm are all allowed to vary as functions of the pre-change sample size. On top of a thorough handling of all the model parameters, we notably allow the edges and missingness to be temporally dependent. To the best of our knowledge, such a general framework has not been rigorously or systematically studied before in the literature. We propose a polynomial-time change point detection algorithm, with a version of the soft-impute algorithm as the imputation sub-routine. By piecing up these established sub-routines, our proposed algorithm achieves sharp detection delay while controlling the overall Type-I error. Extensive numerical experiments support our theoretical findings and demonstrate the effectiveness of our proposed method in practice."]]></description>
<dc:subject>to:NB time_series network_data_analysis change-point_problem re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6d46bde9739c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:change-point_problem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2310.20609">
    <title>[2310.20609] Graph Matching via convex relaxation to the simplex</title>
    <dc:date>2025-04-09T14:54:27+00:00</dc:date>
    <link>https://arxiv.org/abs/2310.20609</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper addresses the Graph Matching problem, which consists of finding the best possible alignment between two input graphs, and has many applications in computer vision, network deanonymization and protein alignment. A common approach to tackle this problem is through convex relaxations of the NP-hard \emph{Quadratic Assignment Problem} (QAP).
"Here, we introduce a new convex relaxation onto the unit simplex and develop an efficient mirror descent scheme with closed-form iterations for solving this problem. Under the correlated Gaussian Wigner model, we show that the simplex relaxation admits a unique solution with high probability. In the noiseless case, this is shown to imply exact recovery of the ground truth permutation. Additionally, we establish a novel sufficiency condition for the input matrix in standard greedy rounding methods, which is less restrictive than the commonly used `diagonal dominance' condition. We use this condition to show exact one-step recovery of the ground truth (holding almost surely) via the mirror descent scheme, in the noiseless setting. We also use this condition to obtain significantly improved conditions for the GRAMPA algorithm [Fan et al. 2019] in the noiseless setting."]]></description>
<dc:subject>to:NB network_data_analysis re:network_differences optimization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5332420e2d77/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2303.04871">
    <title>[2303.04871] Discovering a change point in a time series of organoid networks via the iso-mirror</title>
    <dc:date>2023-03-17T18:12:06+00:00</dc:date>
    <link>https://arxiv.org/abs/2303.04871</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Recent advancements have been made in the development of cell-based in-vitro neuronal networks, or organoids. In order to better understand the network structure of these organoids, [6] propose a method for inferring effective connectivity networks from multi-electrode array data. In this paper, a novel statistical method called spectral mirror estimation [2] is applied to a time series of inferred effective connectivity organoid networks. This method produces a one-dimensional iso-mirror representation of the dynamics of the time series of the networks. A classical change point algorithm is then applied to this representation, which successfully detects a neuroscientifically significant change point coinciding with the time inhibitory neurons start appearing and the percentage of astrocytes increases dramatically [9]. This finding demonstrates the potential utility of applying the iso-mirror dynamic structure discovery method to inferred effective connectivity time series of organoid networks."]]></description>
<dc:subject>to:NB neural_data_analysis network_data_analysis change-point_problem re:network_differences dimension_reduction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5859e41f08a4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:change-point_problem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dimension_reduction"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2209.08223#">
    <title>[2209.08223] Joint Network Topology Inference via a Shared Graphon Model</title>
    <dc:date>2022-11-09T15:45:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2209.08223#</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the problem of estimating the topology of multiple networks from nodal observations, where these networks are assumed to be drawn from the same (unknown) random graph model. We adopt a graphon as our random graph model, which is a nonparametric model from which graphs of potentially different sizes can be drawn. The versatility of graphons allows us to tackle the joint inference problem even for the cases where the graphs to be recovered contain different number of nodes and lack precise alignment across the graphs. Our solution is based on combining a maximum likelihood penalty with graphon estimation schemes and can be used to augment existing network inference methods. The proposed joint network and graphon estimation is further enhanced with the introduction of a robust method for noisy graph sampling information. We validate our proposed approach by comparing its performance against competing methods in synthetic and real-world datasets."]]></description>
<dc:subject>to:NB graphons re:network_differences to_read scooped?</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:76270b6ed49b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphons"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:scooped?"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.cambridge.org/core/elements/apples-to-apples/5F0CCD49D9528EEE5C9CA6C65DEFEAD0">
    <title>Apples to Apples</title>
    <dc:date>2022-07-02T13:36:39+00:00</dc:date>
    <link>https://www.cambridge.org/core/elements/apples-to-apples/5F0CCD49D9528EEE5C9CA6C65DEFEAD0</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Interest in networks in the fields of public management and policy has grown to encompass a wide array of phenomena. However, we lack a stable and empirically verifiable taxonomy for delineating one network class from another. The authors propose all networks and multi-organizational collaborative entities can be sorted into three taxonomic classes: structural-oriented, system-oriented, and purpose-oriented. This Element reviews the intellectual disciplinary histories that have informed our understanding of each of the three classes of networks. It then offers a taxonomic description of each of the three classes of networks. Finally, it provides a field guide for empirically classifying networks. The authors hope is the taxonomy presented will serve as a tool to allow the field to quicken the pace of learning both within and across classes. When we are able to compare apples to apples and avoid inadvertent comparison of apples and oranges, we all get smarter faster."]]></description>
<dc:subject>to:NB social_networks re:network_differences downloaded</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:31b9550fa2d1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:downloaded"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2003.04235">
    <title>[2003.04235] Differential Network Analysis: A Statistical Perspective</title>
    <dc:date>2021-09-23T19:09:44+00:00</dc:date>
    <link>https://arxiv.org/abs/2003.04235</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Networks effectively capture interactions among components of complex systems, and have thus become a mainstay in many scientific disciplines. Growing evidence, especially from biology, suggest that networks undergo changes over time, and in response to external stimuli. In biology and medicine, these changes have been found to be predictive of complex diseases. They have also been used to gain insight into mechanisms of disease initiation and progression. Primarily motivated by biological applications, this article provides a review of recent statistical machine learning methods for inferring networks and identifying changes in their structures.]]></description>
<dc:subject>to:NB re:network_differences shojaie.ali network_data_analysis</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4406cafc2c4d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:shojaie.ali"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2107.07489">
    <title>[2107.07489] Clustering of heterogeneous populations of networks</title>
    <dc:date>2021-08-11T18:42:50+00:00</dc:date>
    <link>https://arxiv.org/abs/2107.07489</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Statistical methods for reconstructing networks from repeated measurements typically assume that all measurements are generated from the same underlying network structure. This need not be the case, however. People's social networks might be different on weekdays and weekends, for instance. Brain networks may differ between healthy patients and those with dementia or other conditions. Here we describe a Bayesian analysis framework for such data that allows for the fact that network measurements may be reflective of multiple possible structures. We define a finite mixture model of the measurement process and derive a fast Gibbs sampling procedure that samples exactly from the full posterior distribution of model parameters. The end result is a clustering of the measured networks into groups with similar structure. We demonstrate the method on both real and synthetic network populations."]]></description>
<dc:subject>in_NB clustering network_data_analysis re:network_differences newman.mark kith_and_kin statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:15a8e80b2b7b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:newman.mark"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2107.11403">
    <title>[2107.11403] A principled (and practical) test for network comparison</title>
    <dc:date>2021-07-27T12:10:21+00:00</dc:date>
    <link>https://arxiv.org/abs/2107.11403</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["How might one test the hypothesis that graphs were sampled from the same distribution? Here, we compare two statistical tests that address this question. The first uses the observed subgraph densities themselves as estimates of those of the underlying distribution. The second test uses a new approach that converts these subgraph densities into estimates of the graph cumulants of the distribution. We demonstrate -- via theory, simulation, and application to real data -- the superior statistical power of using graph cumulants."]]></description>
<dc:subject>to:NB re:network_differences to_read graph_limits to_teach:graphons statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:362abaf62cf2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graph_limits"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:graphons"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2105.14364">
    <title>[2105.14364] Graph Similarity Description: How Are These Graphs Similar?</title>
    <dc:date>2021-06-01T17:48:31+00:00</dc:date>
    <link>https://arxiv.org/abs/2105.14364</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["How do social networks differ across platforms? How do information networks change over time? Answering questions like these requires us to compare two or more graphs. This task is commonly treated as a measurement problem, but numerical answers give limited insight. Here, we argue that if the goal is to gain understanding, we should treat graph similarity assessment as a description problem instead. We formalize this problem as a model selection task using the Minimum Description Length principle, capturing the similarity of the input graphs in a common model and the differences between them in transformations to individual models. To discover good models, we propose Momo, which breaks the problem into two parts and introduces efficient algorithms for each. Through an extensive set of experiments on a wide range of synthetic and real-world graphs, we confirm that Momo works well in practice."]]></description>
<dc:subject>to:NB data_mining network_data_analysis re:network_differences statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ec0f72bf02dc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-1/Optimal-change-point-detection-and-localization-in-sparse-dynamic-networks/10.1214/20-AOS1953.short">
    <title>Optimal change point detection and localization in sparse dynamic networks</title>
    <dc:date>2021-04-12T03:07:34+00:00</dc:date>
    <link>https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-1/Optimal-change-point-detection-and-localization-in-sparse-dynamic-networks/10.1214/20-AOS1953.short</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study the problem of change point localization in dynamic networks models. We assume that we observe a sequence of independent adjacency matrices of the same size, each corresponding to a realization of an unknown inhomogeneous Bernoulli model. The underlying distribution of the adjacency matrices are piecewise constant, and may change over a subset of the time points, called change points. We are concerned with recovering the unknown number and positions of the change points. In our model setting, we allow for all the model parameters to change with the total number of time points, including the network size, the minimal spacing between consecutive change points, the magnitude of the smallest change and the degree of sparsity of the networks. We first identify a region of impossibility in the space of the model parameters such that no change point estimator is provably consistent if the data are generated according to parameters falling in that region. We propose a computationally-simple algorithm for network change point localization, called network binary segmentation, that relies on weighted averages of the adjacency matrices. We show that network binary segmentation is consistent over a range of the model parameters that nearly cover the complement of the impossibility region, thus demonstrating the existence of a phase transition for the problem at hand. Next, we devise a more sophisticated algorithm based on singular value thresholding, called local refinement, that delivers more accurate estimates of the change point locations. Under appropriate conditions, local refinement guarantees a minimax optimal rate for network change point localization while remaining computationally feasible."]]></description>
<dc:subject>to:NB network_data_analysis change-point_problem re:network_differences rinaldo.alessandro</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:339653cd83ea/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:change-point_problem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:rinaldo.alessandro"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.tandfonline.com/doi/full/10.1080/10618600.2020.1844214">
    <title>Nonparametric Anomaly Detection on Time Series of Graphs: Journal of Computational and Graphical Statistics: Vol 0, No 0</title>
    <dc:date>2021-01-10T19:46:11+00:00</dc:date>
    <link>https://www.tandfonline.com/doi/full/10.1080/10618600.2020.1844214</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Identifying change points and/or anomalies in dynamic network structures has become increasingly popular across various domains, from neuroscience to telecommunication to finance. One particular objective of anomaly detection from a neuroscience perspective is the reconstruction of the dynamic manner of brain region interactions. However, most statistical methods for detecting anomalies have the following unrealistic limitation for brain studies and beyond: that is, network snapshots at different time points are assumed to be independent. To circumvent this limitation, we propose a distribution-free framework for anomaly detection in dynamic networks. First, we present each network snapshot of the data as a linear object and find its respective univariate characterization via local and global network topological summaries. Second, we adopt a change point detection method for (weakly) dependent time series based on efficient scores, and enhance the finite sample properties of change point method by approximating the asymptotic distribution of the test statistic using the sieve bootstrap. We apply our method to simulated and to real data, particularly, two functional magnetic resonance imaging (fMRI) datasets and the Enron communication graph. We find that our new method delivers impressively accurate and realistic results in terms of identifying locations of true change points compared to the results reported by competing approaches. The new method promises to offer a deeper insight into the large-scale characterizations and functional dynamics of the brain and, more generally, into the intrinsic structure of complex dynamic networks. Supplemental materials for this article are available online."]]></description>
<dc:subject>to:NB re:network_differences anomaly_detection network_data_analysis</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:da7afaba2487/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:anomaly_detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1911.02741">
    <title>[1911.02741] Improving the Power of a Two-Sample Graph Test with Applications in Connectomics</title>
    <dc:date>2020-12-24T15:46:36+00:00</dc:date>
    <link>https://arxiv.org/abs/1911.02741</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In many applications, there is interest in testing whether two graphs come from the same distribution. However, due to the nature of graph data, classical statistical methods are not directly applicable. When the distribution of each graph is determined by a distribution for vertex latent positions, in particular under the random dot product graph model, a statistical procedure is derived to test whether the two sets of latent positions are equally distributed. We empirically analyze several methods for this problem, and show that adapting Optimal Transport Procrustes (OPT) for aligning latent positions and multiscale graph correlation (MGC) for hypothesis testing to answer this question results in a test which outperforms several existing methods."]]></description>
<dc:subject>to:NB to_read re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e64270d852b9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.09828">
    <title>[2012.09828] Nonparametric Two-Sample Hypothesis Testing for Random Graphs with Negative and Repeated Eigenvalues</title>
    <dc:date>2020-12-18T10:33:02+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.09828</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose a nonparametric two-sample test statistic for low-rank, conditionally independent edge random graphs whose edge probability matrices have negative eigenvalues and arbitrarily close eigenvalues. Our proposed test statistic involves using the maximum mean discrepancy applied to suitably rotated rows of a graph embedding, where the rotation is estimated using optimal transport. We show that our test statistic, appropriately scaled, is consistent for sufficiently dense graphs, and we study its convergence under different sparsity regimes. In addition, we provide empirical evidence suggesting that our novel alignment procedure can perform better than the naïve alignment in practice, where the naïve alignment assumes an eigengap."]]></description>
<dc:subject>to:NB network_data_analysis re:network_differences two-sample_tests</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:aa95516da3d0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:two-sample_tests"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://journals.sagepub.com/doi/full/10.1177/0049124118769113">
    <title>Statistical Power in Longitudinal Network Studies - Christoph Stadtfeld, Tom A. B. Snijders, Christian Steglich, Marijtje van Duijn, 2020</title>
    <dc:date>2020-12-16T20:14:28+00:00</dc:date>
    <link>https://journals.sagepub.com/doi/full/10.1177/0049124118769113</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Longitudinal social network studies can easily suffer from insufficient statistical power. Studies that simultaneously investigate change of network ties and change of nodal attributes (selection and influence studies) are particularly at risk because the number of nodal observations is typically much lower than the number of observed tie variables. This article presents a simulation-based procedure to evaluate statistical power of longitudinal social network studies in which stochastic actor-oriented models are to be applied. Two detailed case studies illustrate how statistical power is strongly affected by network size, number of data collection waves, effect sizes, missing data, and participant turnover. These issues should thus be explored in the design phase of longitudinal social network studies."]]></description>
<dc:subject>to:NB network_data_analysis networks_in_and_over_time snijders.tom.a.b. exponential_family_random_graphs agent-based_models to_teach:baby-nets re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9acccfea16fb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:networks_in_and_over_time"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:snijders.tom.a.b."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:exponential_family_random_graphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:agent-based_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:baby-nets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://journals.aps.org/pre/abstract/10.1103/PhysRevE.102.062301">
    <title>Phys. Rev. E 102, 062301 (2020) - Navigating differential structures in complex networks</title>
    <dc:date>2020-12-15T16:02:36+00:00</dc:date>
    <link>https://journals.aps.org/pre/abstract/10.1103/PhysRevE.102.062301</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Structural changes in a network representation of a system, due to different experimental conditions, different connectivity across layers, or to its time evolution, can provide insight on its organization, function, and on how it responds to external perturbations. The deeper understanding of how gene networks cope with diseases and treatments is maybe the most incisive demonstration of the gains obtained through this differential network analysis point of view, which led to an explosion of new numeric techniques in the last decade. However, where to focus one's attention, or how to navigate through the differential structures in the context of large networks, can be overwhelming even for a few experimental conditions. In this paper, we propose a theory and a methodological implementation for the characterization of shared “structural roles” of nodes simultaneously within and between networks. Inspired by recent methodological advances in chaotic phase synchronization analysis, we show how the information about the shared structures of a set of networks can be split and organized in an automatic fashion, in scenarios with very different (i) community sizes, (ii) total number of communities, and (iii) even for a large number of 100 networks compared using numerical benchmarks generated by a stochastic block model. Then, we investigate how the network size, number of networks, and mean size of communities influence the method performance in a series of Monte Carlo experiments. To illustrate its potential use in a more challenging scenario with real-world data, we show evidence that the method can still split and organize the structural information of a set of four gene coexpression networks obtained from two cell types × two treatments (interferon-β stimulated or control). Aside from its potential use as for automatic feature extraction and preprocessing tool, we discuss that another strength of the method is its “story-telling”-like characterization of the information encoded in a set of networks, which can be used to pinpoint unexpected shared structure, leading to further investigations and providing new insights. Finally, the method is flexible to address different research-field-specific questions, by not restricting what scientific-meaningful characteristic (or relevant feature) of a node shall be used."]]></description>
<dc:subject>to:NB network_data_analysis re:network_differences to_read color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c05c46edf9ce/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.12416">
    <title>[2011.12416] A spectral-based framework for hypothesis testing in populations of networks</title>
    <dc:date>2020-11-26T15:54:58+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.12416</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, we propose a new spectral-based approach to hypothesis testing for populations of networks. The primary goal is to develop a test to determine whether two given samples of networks come from the same random model or distribution. Our test statistic is based on the trace of the third order for a centered and scaled adjacency matrix, which we prove converges to the standard normal distribution as the number of nodes tends to infinity. The asymptotic power guarantee of the test is also provided. The proper interplay between the number of networks and the number of nodes for each network is explored in characterizing the theoretical properties of the proposed testing statistics. Our tests are applicable to both binary and weighted networks, operate under a very general framework where the networks are allowed to be large and sparse, and can be extended to multiple-sample testing. We provide an extensive simulation study to demonstrate the superior performance of our test over existing methods and apply our test to three real datasets."]]></description>
<dc:subject>to:NB to_read network_data_analysis kolaczyk.eric re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1c3db94065fe/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kolaczyk.eric"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.12290">
    <title>[2011.12290] Localism as Secrecy: Efficiency-Secrecy Tradeoffs in the Recruitment of ISIS Foreign Fighters</title>
    <dc:date>2020-11-26T15:48:41+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.12290</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper compares networks of foreign fighters who joined the Islamic State of Iraq and Syria (ISIS) from Europe and the Arabian Peninsula in order to test whether there are differences in their recruitment and how those differences affect the nature of the foreign fighter mobilization. It is the first study to compare different networks of foreign fighters that joined the same group in the same conflict at the same period of time. This study finds that foreign fighter recruitment resembles an efficiency-secrecy tradeoff: in places where recruitment needs to be hidden from legal scrutiny, recruitment networks are decentralized; composed of small and more local recruitment cells. These cells can operate more secretly and the group as a whole is more resilient to disruption. In exchange, it is hard for the group to attract large numbers of recruits. Whereas in places where recruitment could occur more freely, recruitment networks are more hierarchical; comprised of a larger number of recruits with more geographically diverse connections. The hierarchical design of their recruitment networks may be easier to disrupt, but it also helps the group efficiently recruit more followers if left undisturbed. This study concludes that the ISIS foreign fighter recruitment process varied significantly. Researchers and policymakers focused on recruitment and radicalization should therefore carefully frame their results or policies based on the different types of recruitment processes and the various social, political, and legal contexts where their work takes place."]]></description>
<dc:subject>to:NB social_networks terrorism institutions network_data_analysis re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3eeac721d347/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:terrorism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:institutions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1903.11117">
    <title>[1903.11117] Testing for Differences in Stochastic Network Structure</title>
    <dc:date>2020-11-25T14:52:28+00:00</dc:date>
    <link>https://arxiv.org/abs/1903.11117</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["How can one determine whether a community-level treatment, such as the introduction of a social program or trade shock, alters agents' incentives to form links in a network? This paper proposes analogues of a two-sample Kolmogorov-Smirnov test, widely used in the literature to test the null hypothesis of "no treatment effects", for network data. It first specifies a testing problem in which the null hypothesis is that two networks are drawn from the same random graph model. It then describes two randomization tests based on the magnitude of the difference between the networks' adjacency matrices as measured by the 2→2 and ∞→1 operator norms. Power properties of the tests are examined analytically, in simulation, and through two real-world applications. A key finding is that the test based on the ∞→1 norm can be substantially more powerful than that based on the 2→2 norm for the kinds of sparse and degree-heterogeneous networks common in economics."]]></description>
<dc:subject>to:NB network_data_analysis re:network_differences two-sample_tests hypothesis_testing to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ba62b7e5b0dc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:two-sample_tests"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.10079">
    <title>[2011.10079] Improving Functional Connectome Fingerprinting with Degree-Normalization</title>
    <dc:date>2020-11-23T17:35:24+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.10079</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Functional connectivity quantifies the statistical dependencies between the activity of brain regions, measured using neuroimaging data such as functional MRI BOLD time series. The network representation of functional connectivity, called a Functional Connectome (FC), has been shown to contain an individual fingerprint allowing participants identification across consecutive testing sessions. Recently, researchers have focused on the extraction of these fingerprints, with potential applications in personalized medicine.
"Here, we show that a mathematical operation denominated degree-normalization can improve the extraction of FC fingerprints. Degree-normalization has the effect of reducing the excessive influence of strongly connected brain areas in the whole-brain network. We adopt the differential identifiability framework and apply it to both original and degree-normalized FCs of 409 individuals from the Human Connectome Project, in resting-state and 7 fMRI tasks.
"Our results indicate that degree-normalization systematically improves three fingerprinting metrics, namely differential identifiability, identification rate and matching rate. Moreover, the results related to the matching rate metric suggest that individual fingerprints are embedded in a low-dimensional space.
"The results suggest that low-dimensional functional fingerprints lie in part in weakly connected subnetworks of the brain, and that degree-normalization helps uncovering them. This work introduces a simple mathematical operation that could lead to significant improvements in future FCs fingerprinting studies."]]></description>
<dc:subject>to:NB functional_connectivity network_data_analysis re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a0481b33f03b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_connectivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.tandfonline.com/doi/full/10.1080/01621459.2020.1763803">
    <title>Modeling Network Populations via Graph Distances: Journal of the American Statistical Association: Vol 0, No 0</title>
    <dc:date>2020-11-20T19:51:32+00:00</dc:date>
    <link>https://www.tandfonline.com/doi/full/10.1080/01621459.2020.1763803</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This article introduces a new class of models for multiple networks. The core idea is to parameterize a distribution on labeled graphs in terms of a Fréchet mean graph (which depends on a user-specified choice of metric or graph distance) and a parameter that controls the concentration of this distribution about its mean. Entropy is the natural parameter for such control, varying from a point mass concentrated on the Fréchet mean itself to a uniform distribution over all graphs on a given vertex set. We provide a hierarchical Bayesian approach for exploiting this construction, along with straightforward strategies for sampling from the resultant posterior distribution. We conclude by demonstrating the efficacy of our approach via simulation studies and two multiple-network data analysis examples: one drawn from systems biology and the other from neuroscience."

]]></description>
<dc:subject>to:NB to_read network_data_analysis re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:903a47d1a210/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aoas/1593449335">
    <title>Paul , Chen : A random effects stochastic block model for joint community detection in multiple networks with applications to neuroimaging</title>
    <dc:date>2020-11-19T14:30:30+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aoas/1593449335</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["To analyze data from multisubject experiments in neuroimaging studies, we develop a modeling framework for joint community detection in a group of related networks that can be considered as a sample from a population of networks. The proposed random effects stochastic block model facilitates the study of group differences and subject-specific variations in the community structure. The model proposes a putative mean community structure, which is representative of the group or the population under consideration but is not the community structure of any individual component network. Instead, the community memberships of nodes vary in each component network with a transition matrix, thus modeling the variation in community structure across a group of subjects. To estimate the quantities of interest, we propose two methods: a variational EM algorithm and a model-free “two-step” method called Co-OSNTF which is based on nonnegative matrix factorization. We also develop a resampling-based hypothesis test for differences between community structure in two populations both at the whole network level and node level. The methodology is applied to the COBRE dataset, a publicly available fMRI dataset from multisubject experiments involving schizophrenia patients. Our methods reveal an overall putative community structure representative of the group as well as subject-specific variations within each of the two groups, healthy controls and schizophrenia patients. The model has good predictive ability for predicting community structure in subjects from the same population but outside the training sample. Using our network level hypothesis tests, we are able to ascertain statistically significant difference in community structure between the two groups, while our node level tests help determine the nodes that are driving the difference."]]></description>
<dc:subject>to:NB stochastic_block_models community_discovery network_data_analysis re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d4c78edc87c7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_block_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:community_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1597370670">
    <title>Ghoshdastidar , Gutzeit , Carpentier , von Luxburg : Two-sample hypothesis testing for inhomogeneous random graphs</title>
    <dc:date>2020-11-18T21:44:11+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1597370670</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The study of networks leads to a wide range of high-dimensional inference problems. In many practical applications, one needs to draw inference from one or few large sparse networks. The present paper studies hypothesis testing of graphs in this high-dimensional regime, where the goal is to test between two populations of inhomogeneous random graphs defined on the same set of nn vertices. The size of each population mm is much smaller than nn, and can even be a constant as small as 1. The critical question in this context is whether the problem is solvable for small mm.
"We answer this question from a minimax testing perspective. Let PP, QQ be the population adjacencies of two sparse inhomogeneous random graph models, and dd be a suitably defined distance function. Given a population of mm graphs from each model, we derive minimax separation rates for the problem of testing P=QP=Q against d(P,Q)>ρd(P,Q)>ρ. We observe that if mm is small, then the minimax separation is too large for some popular choices of dd, including total variation distance between corresponding distributions. This implies that some models that are widely separated in dd cannot be distinguished for small mm, and hence, the testing problem is generally not solvable in these cases.
"We also show that if m>1m>1, then the minimax separation is relatively small if dd is the Frobenius norm or operator norm distance between PP and QQ. For m=1m=1, only the latter distance provides small minimax separation. Thus, for these distances, the problem is solvable for small mm. We also present near-optimal two-sample tests in both cases, where tests are adaptive with respect to sparsity level of the graphs."]]></description>
<dc:subject>to:NB to_read statistics two-sample_tests network_data_analysis re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:979b239f43f9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:two-sample_tests"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://mitpress.mit.edu/books/changing-connectomes">
    <title>Changing Connectomes | The MIT Press</title>
    <dc:date>2020-09-21T03:49:14+00:00</dc:date>
    <link>https://mitpress.mit.edu/books/changing-connectomes</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The human brain undergoes massive changes during its development, from early childhood and the teenage years to adulthood and old age. Across a wide range of species, from C. elegans and fruit flies to mice, monkeys, and humans, information about brain connectivity (connectomes) at different stages is now becoming available. New approaches in network neuroscience can be used to analyze the topological, spatial, and dynamical organization of such connectomes. In Changing Connectomes, Marcus Kaiser provides an up-to-date overview of the field of connectomics and introduces concepts and mechanisms underlying brain network changes during evolution and development. 
"Drawing on a range of results from experimental, clinical, and computational studies, Kaiser describes changes during healthy brain maturation and during brain network disorders (including such neurodevelopmental conditions as schizophrenia and depression), brain injury, and neurodegenerative disorders including dementia. He argues that brain stimulation is an area where understanding connectome development could help in assessing long-term effects of interventions. Changing Connectomes is a suitable starting point for researchers who are new to the field of connectomics, and also for researchers who are interested in the link between brain network organization and brain and cognitive development in health and disease. Matlab/Octave code examples available at the MIT Press website will allow computational neuroscience researchers to understand and extend the shown mechanisms of connectome development."]]></description>
<dc:subject>to:NB books:noted re:network_differences neuroscience books:suggest_to_library</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:055dc8ff2364/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:books:noted"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:books:suggest_to_library"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1812.00769">
    <title>[1812.00769] Testing Changes in Communities for the Stochastic Block Model</title>
    <dc:date>2019-11-30T02:11:43+00:00</dc:date>
    <link>https://arxiv.org/abs/1812.00769</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose and analyze the problems of \textit{community goodness-of-fit and two-sample testing} for stochastic block models (SBM), where changes arise due to modification in community memberships of nodes. Motivated by practical applications, we consider the challenging sparse regime, where expected node degrees are constant, and the inter-community mean degree (b) scales proportionally to intra-community mean degree (a). Prior work has sharply characterized partial or full community recovery in terms of a "signal-to-noise ratio" (SNR) based on a and b. For both problems, we propose computationally-efficient tests that can succeed far beyond the regime where recovery of community membership is even possible. Overall, for large changes, s≫n‾√, we need only SNR=O(1) whereas a naïve test based on community recovery with O(s) errors requires SNR=Θ(logn). Conversely, in the small change regime, s≪n‾√, via an information-theoretic lower bound, we show that, surprisingly, no algorithm can do better than the naïve algorithm that first estimates the community up to O(s) errors and then detects changes. We validate these phenomena numerically on SBMs and on real-world datasets as well as Markov Random Fields where we only observe node data rather than the existence of links."]]></description>
<dc:subject>to:NB re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6c80fa5129c6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1811.08763">
    <title>[1811.08763] Comparison of Brain Networks based on Predictive Models of Connectivity</title>
    <dc:date>2019-11-09T23:25:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1811.08763</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this study we adopt predictive modelling to identify simultaneously commonalities and differences in multi-modal brain networks acquired within subjects. Typically, predictive modelling of functional connectomes from structural connectomes explores commonalities across multimodal imaging data. However, direct application of multivariate approaches such as sparse Canonical Correlation Analysis (sCCA) applies on the vectorised elements of functional connectivity across subjects and it does not guarantee that the predicted models of functional connectivity are Symmetric Positive Matrices (SPD). We suggest an elegant solution based on the transportation of the connectivity matrices on a Riemannian manifold, which notably improves the prediction performance of the model. Randomised lasso is used to alleviate the dependency of the sCCA on the lasso parameters and control the false positive rate. Subsequently, the binomial distribution is exploited to set a threshold statistic that reflects whether a connection is selected or rejected by chance. Finally, we estimate the sCCA loadings based on a de-noising approach that improves the estimation of the coefficients. We validate our approach based on resting-state fMRI and diffusion weighted MRI data. Quantitative validation of the prediction performance shows superior performance, whereas qualitative results of the identification process are promising."]]></description>
<dc:subject>to:NB functional_connectivity fmri neuroscience re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:32d86143e10e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_connectivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fmri"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1901.08521">
    <title>[1901.08521] Brain Network Topology Maps the Dysfunctional Substrate of Cognitive Processes in Schizophrenia</title>
    <dc:date>2019-10-29T14:27:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1901.08521</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Using a novel network analysis of spontaneous low-frequency functional MRI data recorded at rest, we study the functional network that describes the extent of synchronization among different areas of the brain. Comparing forty-four medicated patients and forty healthy subjects, we detected significant differences in the robustness of these functional networks. Such differences resulted in a larger resistance to edge removal (disconnection) in the graph of schizophrenic patients as compared to healthy controls. This paper shows that the distribution of connectivity strength among brain regions is spatially more homogeneous in schizophrenic patients with respect to healthy ones. As a consequence, the precise hierarchical modularity of healthy brains is crumbled in schizophrenic ones, making possible a peculiar arrangement of region-to-region interaction that, in turns, produces several topologically equivalent backbones of the whole functional brain network. We hypothesize that the manifold nature of the basal scheme of functional organization within the brain, together with its altered hierarchical modularity, contributes to positive symptoms of schizophrenia. Our work also fits the disconnection hypothesis that describes schizophrenia as a brain disorder, characterized by abnormal functional integration among brain regions."]]></description>
<dc:subject>to:NB functional_connectivity neural_data_analysis fmri schizophrenia re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cbd82d06c504/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_connectivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fmri"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:schizophrenia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.02301">
    <title>[1910.02301] Change Detection in Noisy Dynamic Networks: A Spectral Embedding Approach</title>
    <dc:date>2019-10-24T17:56:28+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.02301</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Change detection in dynamic networks is an important problem in many areas, such as fraud detection, cyber intrusion detection and health care monitoring. It is a challenging problem because it involves a time sequence of graphs, each of which is usually very large and sparse with heterogeneous vertex degrees, resulting in a complex, high dimensional mathematical object. Spectral embedding methods provide an effective way to transform a graph to a lower dimensional latent Euclidean space that preserves the underlying structure of the network. Although change detection methods that use spectral embedding are available, they do not address sparsity and degree heterogeneity that usually occur in noisy real-world graphs and a majority of these methods focus on changes in the behaviour of the overall network.
"In this paper, we adapt previously developed techniques in spectral graph theory and propose a novel concept of applying Procrustes techniques to embedded points for vertices in a graph to detect changes in entity behaviour. Our spectral embedding approach not only addresses sparsity and degree heterogeneity issues, but also obtains an estimate of the appropriate embedding dimension. We call this method CDP (change detection using Procrustes analysis). We demonstrate the performance of CDP through extensive simulation experiments and a real-world application. CDP successfully detects various types of vertex-based changes including (i) changes in vertex degree, (ii) changes in community membership of vertices, and (iii) unusual increase or decrease in edge weight between vertices. The change detection performance of CDP is compared with two other baseline methods that employ alternative spectral embedding approaches. In both cases, CDP generally shows superior performance."]]></description>
<dc:subject>to:NB network_data_analysis spectral_methods re:network_differences change-point_problem statistics networks_in_and_over_time</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:947dcaee813f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:spectral_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:change-point_problem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:networks_in_and_over_time"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1710.02761">
    <title>[1710.02761] Fréchet Analysis Of Variance For Random Objects</title>
    <dc:date>2019-10-22T13:25:25+00:00</dc:date>
    <link>https://arxiv.org/abs/1710.02761</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Fréchet mean and variance provide a way of obtaining mean and variance for general metric space valued random variables and can be used for statistical analysis of data objects that lie in abstract spaces devoid of algebraic structure and operations. Examples of such spaces include covariance matrices, graph Laplacians of networks and univariate probability distribution functions. We derive a central limit theorem for Fréchet variance under mild regularity conditions, utilizing empirical process theory, and also provide a consistent estimator of the asymptotic variance. These results lead to a test to compare k populations based on Fréchet variance for general metric space valued data objects, with emphasis on comparing means and variances. We examine the finite sample performance of this inference procedure through simulation studies for several special cases that include probability distributions and graph Laplacians, which leads to tests to compare populations of networks. The proposed methodology has good finite sample performance in simulations for different kinds of random objects. We illustrate the proposed methods with data on mortality profiles of various countries and resting state Functional Magnetic Resonance Imaging data."]]></description>
<dc:subject>to:NB geometry statistics re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e593b4e76eef/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aoas/1571277767">
    <title>Arroyo Relión , Kessler , Levina , Taylor : Network classification with applications to brain connectomics</title>
    <dc:date>2019-10-19T18:00:34+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aoas/1571277767</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["While statistical analysis of a single network has received a lot of attention in recent years, with a focus on social networks, analysis of a sample of networks presents its own challenges which require a different set of analytic tools. Here we study the problem of classification of networks with labeled nodes, motivated by applications in neuroimaging. Brain networks are constructed from imaging data to represent functional connectivity between regions of the brain, and previous work has shown the potential of such networks to distinguish between various brain disorders, giving rise to a network classification problem. Existing approaches tend to either treat all edge weights as a long vector, ignoring the network structure, or focus on graph topology as represented by summary measures while ignoring the edge weights. Our goal is to design a classification method that uses both the individual edge information and the network structure of the data in a computationally efficient way, and that can produce a parsimonious and interpretable representation of differences in brain connectivity patterns between classes. We propose a graph classification method that uses edge weights as predictors but incorporates the network nature of the data via penalties that promote sparsity in the number of nodes, in addition to the usual sparsity penalties that encourage selection of edges. We implement the method via efficient convex optimization and provide a detailed analysis of data from two fMRI studies of schizophrenia."]]></description>
<dc:subject>to:NB network_data_analysis re:network_differences statistics levina.elizaveta</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:020360dd1a4e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:levina.elizaveta"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1703.03862">
    <title>[1703.03862] Joint Embedding of Graphs</title>
    <dc:date>2019-10-19T00:18:00+00:00</dc:date>
    <link>https://arxiv.org/abs/1703.03862</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Feature extraction and dimension reduction for networks is critical in a wide variety of domains. Efficiently and accurately learning features for multiple graphs has important applications in statistical inference on graphs. We propose a method to jointly embed multiple undirected graphs. Given a set of graphs, the joint embedding method identifies a linear subspace spanned by rank one symmetric matrices and projects adjacency matrices of graphs into this subspace. The projection coefficients can be treated as features of the graphs, while the embedding components can represent vertex features. We also propose a random graph model for multiple graphs that generalizes other classical models for graphs. We show through theory and numerical experiments that under the model, the joint embedding method produces estimates of parameters with small errors. Via simulation experiments, we demonstrate that the joint embedding method produces features which lead to state of the art performance in classifying graphs. Applying the joint embedding method to human brain graphs, we find it extracts interpretable features with good prediction accuracy in different tasks."]]></description>
<dc:subject>to:NB network_visualization re:network_differences network_data_analysis</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e680cc7873b4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1908.03836">
    <title>[1908.03836] Hypothesis Testing for Network Data with Power Enhancement</title>
    <dc:date>2019-10-11T22:15:00+00:00</dc:date>
    <link>https://arxiv.org/abs/1908.03836</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Comparing two population means of network data is of paramount importance in a wide range of scientific applications. Many existing network inference solutions focus on global testing of entire networks, without comparing individual network links. Besides, the observed data often take the form of vectors or matrices, and the problem is formulated as comparing two covariance or precision matrices under a normal or matrix normal distribution. Moreover, many tests suffer from a limited power under a small sample size. In this article, we tackle the problem of network comparison, both global and simultaneous inferences, when the data come in a different format, i.e., in the form of a collection of symmetric matrices, each of which encodes the network structure of an individual subject. Such data format commonly arises in applications such as brain connectivity analysis and clinical genomics. We no longer require the underlying data to follow a normal distribution, but instead impose some moment conditions that are easily satisfied for numerous types of network data. Furthermore, we propose a power enhancement procedure, and show that it can control the false discovery, while it has the potential to substantially enhance the power of the test. We investigate the efficacy of our testing procedure through both an asymptotic analysis and a simulation study under a finite sample size. We further illustrate our method with an example of brain structural connectivity analysis."]]></description>
<dc:subject>to:NB re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c9d39069305a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.13253">
    <title>[1909.13253] Changing the tune: mixtures of network models that vary in time</title>
    <dc:date>2019-10-01T16:30:38+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.13253</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Many of the complex systems we study in their representation as networks are growing objects, evolving by the addition of nodes and links over time. The rules governing this growth are attributed to mechanisms such as preferential attachment and triangle closure. We demonstrate a method for estimating the relative roles of these mechanisms, and further, investigating how they change as the network evolves. We show that a rich class of network evolution models can be built from a weighted mixture of these model mechanisms. Using a likelihood based formulation we show how to calculate the optimal mixture for a given set of observations of network data, and show that this framework can be used to distinguish competing models that are indistinguishable by their summary statistics. Using real data from Facebook user interactions, we show that we can improve the ability of a model to reproduce network statistics using tuned model mixtures. We further investigate the idea that the underlying model of a network can change in time, for example, a technology based network might respond to changes in the underlying technology or a financial network might respond to economic shocks. Using artificial data we show that we can recapture the time at which a known change occurred. We use the Enron email dataset to show that we can estimate how mixtures of models change over time."]]></description>
<dc:subject>to:NB network_formation time_series statistics network_data_analysis re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1bb2b6671f35/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_formation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.13464">
    <title>[1909.13464] Network Differential Connectivity Analysis</title>
    <dc:date>2019-10-01T16:17:41+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.13464</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Identifying differences in networks has become a canonical problem in many biological applications. Here, we focus on testing whether two Gaussian graphical models are the same. Existing methods try to accomplish this goal by either directly comparing their estimated structures, or testing the null hypothesis that the partial correlation matrices are equal. However, estimation approaches do not provide measures of uncertainty, e.g., p-values, which are crucial in drawing scientific conclusions. On the other hand, existing testing approaches could lead to misleading results in some cases. To address these shortcomings, we propose a qualitative hypothesis testing framework, which tests whether the connectivity patterns in the two networks are the same. Our framework is especially appropriate if the goal is to identify nodes or edges that are differentially connected. No existing approach could test such hypotheses and provide corresponding measures of uncertainty, e.g., p-values. We investigate theoretical and numerical properties of our proposal and illustrate its utility in biological applications. Theoretically, we show that under appropriate conditions, our proposal correctly controls the type-I error rate in testing the qualitative hypothesis. Empirically, we demonstrate the performance of our proposal using simulation datasets and applications in cancer genetics and brain imaging studies."]]></description>
<dc:subject>to:NB network_data_analysis hypothesis_testing two-sample_tests statistics re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:612fcc0d1d37/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:two-sample_tests"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1707.00833">
    <title>[1707.00833] Two-sample Hypothesis Testing for Inhomogeneous Random Graphs</title>
    <dc:date>2019-07-18T10:54:20+00:00</dc:date>
    <link>https://arxiv.org/abs/1707.00833</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The study of networks leads to a wide range of high dimensional inference problems. In many practical applications, one needs to draw inference from one or few large sparse networks. The present paper studies hypothesis testing of graphs in this high-dimensional regime, where the goal is to test between two populations of inhomogeneous random graphs defined on the same set of n vertices. The size of each population m is much smaller than n, and can even be a constant as small as 1. The critical question in this context is whether the problem is solvable for small m. 
"We answer this question from a minimax testing perspective. Let P,Q be the population adjacencies of two sparse inhomogeneous random graph models, and d be a suitably defined distance function. Given a population of m graphs from each model, we derive minimax separation rates for the problem of testing P=Q against d(P,Q)>ρ. We observe that if m is small, then the minimax separation is too large for some popular choices of d, including total variation distance between corresponding distributions. This implies that some models that are widely separated in d cannot be distinguished for small m, and hence, the testing problem is generally not solvable in these cases. 
"We also show that if m>1, then the minimax separation is relatively small if d is the Frobenius norm or operator norm distance between P and Q. For m=1, only the latter distance provides small minimax separation. Thus, for these distances, the problem is solvable for small m. We also present near-optimal two-sample tests in both cases, where tests are adaptive with respect to sparsity level of the graphs."]]></description>
<dc:subject>hypothesis_testing network_data_analysis statistics re:network_differences to_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:96f336abd219/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1701.00505">
    <title>[1701.00505] Statistical inference for network samples using subgraph counts</title>
    <dc:date>2019-05-30T16:04:10+00:00</dc:date>
    <link>https://arxiv.org/abs/1701.00505</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider that a network is an observation, and a collection of observed networks forms a sample. In this setting, we provide methods to test whether all observations in a network sample are drawn from a specified model. We achieve this by deriving, under the null of the graphon model, the joint asymptotic properties of average subgraph counts as the number of observed networks increases but the number of nodes in each network remains finite. In doing so, we do not require that each observed network contains the same number of nodes, or is drawn from the same distribution. Our results yield joint confidence regions for subgraph counts, and therefore methods for testing whether the observations in a network sample are drawn from: a specified distribution, a specified model, or from the same model as another network sample. We present simulation experiments and an illustrative example on a sample of brain networks where we find that highly creative individuals' brains present significantly more short cycles."]]></description>
<dc:subject>to:NB to_read network_data_analysis graphical_models re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f26ad51997c2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1905.11249">
    <title>[1905.11249] Network properties of healthy and Alzheimer's brains</title>
    <dc:date>2019-05-28T16:49:29+00:00</dc:date>
    <link>https://arxiv.org/abs/1905.11249</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Small-world structures are often used to describe structural connections in the brain. In this work, we compare the structural connection of cortical areas of a healthy brain and a brain affected by Alzheimer's disease with artificial small-world networks. Based on statistics analysis, we demonstrate that similar small-world networks can be constructed using Newman-Watts procedure. The network quantifiers of both structural matrices are identified inside the probabilistic valley. Despite of similarities between structural connection matrices and sampled small-world networks, increased assortativity can be found in the Alzheimer brain. Our results indicate that network quantifiers can be helpful to identify abnormalities in real structural connection matrices."]]></description>
<dc:subject>to:NB neural_data_analysis network_data_analysis re:network_differences statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8a139ad87659/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1905.10302">
    <title>[1905.10302] Monitoring dynamic networks: a simulation-based strategy for comparing monitoring methods and a comparative study</title>
    <dc:date>2019-05-27T15:14:26+00:00</dc:date>
    <link>https://arxiv.org/abs/1905.10302</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Recently there has been a lot of interest in monitoring and identifying changes in dynamic networks, which has led to the development of a variety of monitoring methods. Unfortunately, these methods have not been systematically compared; moreover, new methods are often designed for a specialized use case. In light of this, we propose the use of simulation to compare the performance of network monitoring methods over a variety of dynamic network changes. Using our family of simulated dynamic networks, we compare the performance of several state-of-the-art social network monitoring methods in the literature. We compare their performance over a variety of types of change; we consider both increases in communication levels, node propensity change as well as changes in community structure. We show that there does not exist one method that is uniformly superior to the others; the best method depends on the context and the type of change one wishes to detect. As such, we conclude that a variety of methods is needed for network monitoring and that it is important to understand in which scenarios a given method is appropriate."]]></description>
<dc:subject>to:NB network_data_analysis change-point_problem re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d8cd4917ec41/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:change-point_problem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1812.03090">
    <title>[1812.03090] Change Point Estimation in a Dynamic Stochastic Block Model</title>
    <dc:date>2019-05-10T03:34:33+00:00</dc:date>
    <link>https://arxiv.org/abs/1812.03090</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the problem of estimating the location of a single change point in a dynamic stochastic block model. We propose two methods of estimating the change point, together with the model parameters. The first employs a least squares criterion function and takes into consideration the full structure of the stochastic block model and is evaluated at each point in time. Hence, as an intermediate step, it requires estimating the community structure based on a clustering algorithm at every time point. The second method comprises of the following two steps: in the first one, a least squares function is used and evaluated at each time point, but ignores the community structures and just considers a random graph generating mechanism exhibiting a change point. Once the change point is identified, in the second step, all network data before and after it are used together with a clustering algorithm to obtain the corresponding community structures and subsequently estimate the generating stochastic block model parameters. A comparison between these two methods is illustrated. Further, for both methods under their respective identifiability and certain additional regularity conditions, we establish rates of convergence and derive the asymptotic distributions of the change point estimators. The results are illustrated on synthetic data."]]></description>
<dc:subject>to:NB re:network_differences network_data_analysis statistics change-point_problem</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5f7b8989eab9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:change-point_problem"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1904.07414">
    <title>[1904.07414] Metrics for Graph Comparison: A Practitioner's Guide</title>
    <dc:date>2019-05-10T03:14:52+00:00</dc:date>
    <link>https://arxiv.org/abs/1904.07414</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Comparison of graph structure is a ubiquitous task in data analysis and machine learning, with diverse applications in fields such as neuroscience, cyber security, social network analysis, and bioinformatics, among others. Discovery and comparison of structures such as modular communities, rich clubs, hubs, and trees in data in these fields yields insight into the generative mechanisms and functional properties of the graph. 
"Often, two graphs are compared via a pairwise distance measure, with a small distance indicating structural similarity and vice versa. Common choices include spectral distances (also known as λ distances) and distances based on node affinities. However, there has of yet been no comparative study of the efficacy of these distance measures in discerning between common graph topologies and different structural scales. 
"In this work, we compare commonly used graph metrics and distance measures, and demonstrate their ability to discern between common topological features found in both random graph models and empirical datasets. We put forward a multi-scale picture of graph structure, in which the effect of global and local structure upon the distance measures is considered. We make recommendations on the applicability of different distance measures to empirical graph data problem based on this multi-scale view. Finally, we introduce the Python library NetComp which implements the graph distances used in this work."]]></description>
<dc:subject>to:NB network_data_analysis to_teach:baby-nets re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e9b4662019cf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:baby-nets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1903.02129">
    <title>[1903.02129] Graph-aware linear mixed effects models for brain connectivity networks</title>
    <dc:date>2019-04-11T00:32:54+00:00</dc:date>
    <link>https://arxiv.org/abs/1903.02129</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Neuroimaging data on functional connections in the brain are frequently represented by weighted networks. These networks share the same set of labeled nodes corresponding to a fixed atlas of the brain, while each subject's network has their own edge weights. We propose a method for modeling such brain networks via linear mixed effects models, which takes advantage of the community structure, or functional regions, known to be present in the brain. The model allows for comparing two populations, such as patients and healthy controls, globally, at functional systems level, and at individual edge level, with systems-level inference in particular allowing for a biologically meaningful interpretation. We incorporate correlation between edge weights into the model by allowing for a general variance structure, and show this leads to much more accurate inference. A thorough study comparing schizophrenics to healthy controls illustrates the full potential of our methods, and obtains results consistent with the medical literature on schizophrenia."]]></description>
<dc:subject>to:NB network_data_analysis levina.elizaveta statistics neuroscience re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a4eceadcc3e5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:levina.elizaveta"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1904.03348">
    <title>[1904.03348] Goodness of Fit Testing for Dynamic Networks</title>
    <dc:date>2019-04-11T00:09:18+00:00</dc:date>
    <link>https://arxiv.org/abs/1904.03348</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Numerous networks in the real world change over time, in the sense that nodes and edges enter and leave the networks. Various dynamic random graph models have been proposed to explain the macroscopic properties of these systems and to provide a foundation for statistical inferences and predictions. It is of interest to have a rigorous way to determine how well these models match observed networks. We thus ask the following goodness of fit question: given a sequence of observations/snapshots of a growing random graph, along with a candidate model M, can we determine whether the snapshots came from M or from some arbitrary alternative model that is well-separated from M in some natural metric? We formulate this problem precisely and boil it down to goodness of fit testing for graph-valued, infinite-state Markov processes and exhibit and analyze a test based on a procedure that we call non-stationary sampling for a natural class of models."]]></description>
<dc:subject>to:NB network_data_analysis statistics goodness-of-fit re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:886408724918/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:goodness-of-fit"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1801.07351">
    <title>[1801.07351] Tracking network dynamics: a survey of distances and similarity metrics</title>
    <dc:date>2019-01-14T21:17:52+00:00</dc:date>
    <link>https://arxiv.org/abs/1801.07351</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["From longitudinal biomedical studies to social networks, graphs have emerged as a powerful framework for describing evolving interactions between agents in complex systems. In such studies, after pre-processing, the data can be represented by a set of graphs, each representing a system's state at different points in time. The analysis of the system's dynamics depends on the selection of the appropriate analytical tools. After characterizing similarities between states, a critical step lies in the choice of a distance between graphs capable of reflecting such similarities. While the literature offers a number of distances that one could a priori choose from, their properties have been little investigated and no guidelines regarding the choice of such a distance have yet been provided. In particular, most graph distances consider that the nodes are exchangeable and do not take into account node identities. Accounting for the alignment of the graphs enables us to enhance these distances' sensitivity to perturbations in the network and detect important changes in graph dynamics. Thus the selection of an adequate metric is a decisive --yet delicate--practical matter. 
"In the spirit of Goldenberg, Zheng and Fienberg's seminal 2009 review, the purpose of this article is to provide an overview of commonly-used graph distances and an explicit characterization of the structural changes that they are best able to capture. We use as a guiding thread to our discussion the application of these distances to the analysis of both a longitudinal microbiome dataset and a brain fMRI study. We show examples of using permutation tests to detect the effect of covariates on the graphs' variability. Synthetic examples provide intuition as to the qualities and drawbacks of the different distances. Above all, we provide some guidance for choosing one distance over another in certain types of applications."]]></description>
<dc:subject>to:NB network_data_analysis re:network_differences holmes.susan to_teach:baby-nets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:162b8af99015/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:holmes.susan"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:baby-nets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1809.02512">
    <title>[1809.02512] Multi-level hypothesis testing for populations of heterogeneous networks</title>
    <dc:date>2018-09-19T14:25:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1809.02512</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this work, we consider hypothesis testing and anomaly detection on datasets where each observation is a weighted network. Examples of such data include brain connectivity networks from fMRI flow data, or word co-occurrence counts for populations of individuals. Current approaches to hypothesis testing for weighted networks typically requires thresholding the edge-weights, to transform the data to binary networks. This results in a loss of information, and outcomes are sensitivity to choice of threshold levels. Our work avoids this, and we consider weighted-graph observations in two situations, 1) where each graph belongs to one of two populations, and 2) where entities belong to one of two populations, with each entity possessing multiple graphs (indexed e.g. by time). Specifically, we propose a hierarchical Bayesian hypothesis testing framework that models each population with a mixture of latent space models for weighted networks, and then tests populations of networks for differences in distribution over components. Our framework is capable of population-level, entity-specific, as well as edge-specific hypothesis testing. We apply it to synthetic data and three real-world datasets: two social media datasets involving word co-occurrences from discussions on Twitter of the political unrest in Brazil, and on Instagram concerning Attention Deficit Hyperactivity Disorder (ADHD) and depression drugs, and one medical dataset involving fMRI brain-scans of human subjects. The results show that our proposed method has lower Type I error and higher statistical power compared to alternatives that need to threshold the edge weights. Moreover, they show our proposed method is better suited to deal with highly heterogeneous datasets."]]></description>
<dc:subject>to_read re:network_differences network_data_analysis statistics hypothesis_testing functional_connectivity neuroscience neville.jennifer in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:062f9a168404/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_connectivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neville.jennifer"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1804.03665">
    <title>[1804.03665] An information-theoretic, all-scales approach to comparing networks</title>
    <dc:date>2018-04-16T13:18:27+00:00</dc:date>
    <link>https://arxiv.org/abs/1804.03665</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["As network research becomes more sophisticated, it is more common than ever for researchers to find themselves not studying a single network but needing to analyze sets of networks. An important task when working with sets of networks is network comparison, developing a similarity or distance measure between networks so that meaningful comparisons can be drawn. The best means to accomplish this task remains an open area of research. Here we introduce a new measure to compare networks, the Portrait Divergence, that is mathematically principled, incorporates the topological characteristics of networks at all structural scales, and is general-purpose and applicable to all types of networks. An important feature of our measure that enables many of its useful properties is that it is based on a graph invariant, the network portrait. We test our measure on both synthetic graphs and real world networks taken from protein interaction data, neuroscience, and computational social science applications. The Portrait Divergence reveals important characteristics of multilayer and temporal networks extracted from data."]]></description>
<dc:subject>to_read statistics re:network_differences information_theory bollt.erik_m. in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bcad15316737/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bollt.erik_m."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1711.02123">
    <title>[1711.02123] Consistency of Maximum Likelihood for Continuous-Space Network Models</title>
    <dc:date>2017-11-08T16:05:51+00:00</dc:date>
    <link>https://arxiv.org/abs/1711.02123</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Network analysis needs tools to infer distributions over graphs of arbitrary size from a single graph. Assuming the distribution is generated by a continuous latent space model which obeys certain natural symmetry and smoothness properties, we establish three levels of consistency for non-parametric maximum likelihood inference as the number of nodes grows: (i) the estimated locations of all nodes converge in probability on their true locations; (ii) the distribution over locations in the latent space converges on the true distribution; and (iii) the distribution over graphs of arbitrary size converges."]]></description>
<dc:subject>in_NB network_data_analysis statistics self-promotion to:blog re:network_differences re:hyperbolic_networks to_teach:baby-nets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d1f0f5a5f14c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:self-promotion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:hyperbolic_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:baby-nets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.journals.uchicago.edu/doi/10.1086/597791">
    <title>Murder by Structure: Dominance Relations and the Social Structure of Gang Homicide: American Journal of Sociology: Vol 115, No 1</title>
    <dc:date>2017-08-26T16:54:41+00:00</dc:date>
    <link>http://www.journals.uchicago.edu/doi/10.1086/597791</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Most sociological theories consider murder an outcome of the differential distribution of individual, neighborhood, or social characteristics. And while such studies explain variation in aggregate homicide rates, they do not explain the social order of murder, that is, who kills whom, when, where, and for what reason. This article argues that gang murder is best understood not by searching for its individual determinants but by examining the social networks of action and reaction that create it. In short, the social structure of gang murder is defined by the manner in which social networks are constructed and by people's placement in them. The author uses a network approach and incident‐level homicide records to recreate and analyze the structure of gang murders in Chicago. Findings demonstrate that individual murders between gangs create an institutionalized network of group conflict, net of any individual's participation or motive. Within this network, murders spread through an epidemic‐like process of social contagion as gangs evaluate the highly visible actions of others in their local networks and negotiate dominance considerations that arise during violent incidents."

--- Uses the same  old methods for detecting contagion as Christakis-Fowler; perhaps more plausible here?]]></description>
<dc:subject>to:NB have_read social_networks violence contagion social_influence sociology re:network_differences honor re:homophily_and_confounding</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5285fbb6155d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:violence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:contagion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_influence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sociology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:honor"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:homophily_and_confounding"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1311.6425">
    <title>[1311.6425] Robust Multimodal Graph Matching: Sparse Coding Meets Graph Matching</title>
    <dc:date>2016-12-01T20:28:23+00:00</dc:date>
    <link>https://arxiv.org/abs/1311.6425</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Graph matching is a challenging problem with very important applications in a wide range of fields, from image and video analysis to biological and biomedical problems. We propose a robust graph matching algorithm inspired in sparsity-related techniques. We cast the problem, resembling group or collaborative sparsity formulations, as a non-smooth convex optimization problem that can be efficiently solved using augmented Lagrangian techniques. The method can deal with weighted or unweighted graphs, as well as multimodal data, where different graphs represent different types of data. The proposed approach is also naturally integrated with collaborative graph inference techniques, solving general network inference problems where the observed variables, possibly coming from different modalities, are not in correspondence. The algorithm is tested and compared with state-of-the-art graph matching techniques in both synthetic and real graphs. We also present results on multimodal graphs and applications to collaborative inference of brain connectivity from alignment-free functional magnetic resonance imaging (fMRI) data. The code is publicly available."]]></description>
<dc:subject>to:NB to_read network_comparison graph_theory network_data_analysis statistics information_theory re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:596102d3a2b4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_comparison"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graph_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1202.1561">
    <title>[1202.1561] Tree models for difference and change detection in a complex environment</title>
    <dc:date>2016-11-30T01:56:46+00:00</dc:date>
    <link>https://arxiv.org/abs/1202.1561</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A new family of tree models is proposed, which we call "differential trees." A differential tree model is constructed from multiple data sets and aims to detect distributional differences between them. The new methodology differs from the existing difference and change detection techniques in its nonparametric nature, model construction from multiple data sets, and applicability to high-dimensional data. Through a detailed study of an arson case in New Zealand, where an individual is known to have been laying vegetation fires within a certain time period, we illustrate how these models can help detect changes in the frequencies of event occurrences and uncover unusual clusters of events in a complex environment."]]></description>
<dc:subject>decision_trees statistics re:network_differences have_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:047cb0ac88d5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:decision_trees"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://papers.nips.cc/paper/3294-modeling-homophily-and-stochastic-equivalence-in-symmetric-relational-data">
    <title>Modeling homophily and stochastic equivalence in symmetric relational data</title>
    <dc:date>2016-05-10T17:44:22+00:00</dc:date>
    <link>http://papers.nips.cc/paper/3294-modeling-homophily-and-stochastic-equivalence-in-symmetric-relational-data</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This article discusses a latent variable model for inference and prediction of symmetric relational data. The model, based on the idea of the eigenvalue decomposition, represents the relationship between two nodes as the weighted inner-product of node-specific vectors of latent characteristics. This eigenmodel'' generalizes other popular latent variable models, such as latent class and distance models: It is shown mathematically that any latent class or distance model has a representation as an eigenmodel, but not vice-versa. The practical implications of this are examined in the context of three real datasets, for which the eigenmodel has as good or better out-of-sample predictive performance than the other two models."

--- Why the EXPLETIVE hadn't I read this before?]]></description>
<dc:subject>network_data_analysis re:network_differences statistics hoff.peter community_discovery inference_to_latent_objects cross-validation re:XV_for_networks have_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2af1af617696/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hoff.peter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:community_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inference_to_latent_objects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1511.02976">
    <title>[1511.02976] Dynamic fluctuations in global brain network topology characterize functional states during rest and behavior</title>
    <dc:date>2016-02-15T21:09:17+00:00</dc:date>
    <link>http://arxiv.org/abs/1511.02976</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Higher brain function relies upon the ability to flexibly integrate information across specialized communities of macroscopic brain regions, but it is unclear how this mechanism manifests over time. Here we characterized patterns of time-resolved functional connectivity using resting state and task fMRI data from a large cohort of unrelated subjects. Our results demonstrate that dynamic fluctuations in network structure during the resting state reflect transitions between states of integrated and segregated network topology. These patterns were altered during task performance, demonstrating a higher level of network integration that tracked with the complexity of the task and correlated with effective behavioral performance. Replication analysis demonstrated that these results were reproducible across sessions, sample populations and datasets. Together these results provide insight into the brain's coordination between integration and segregation and highlight key principles underlying the reorganization of the network architecture of the brain during both rest and behavior."]]></description>
<dc:subject>to:NB to_read functional_connectivity neural_data_analysis neuroscience network_data_analysis re:network_differences poldrack.russell</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e6b27240f6c4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_connectivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:poldrack.russell"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1602.01130">
    <title>[1602.01130] GraphPrints: Towards a Graph Analytic Method for Network Anomaly Detection</title>
    <dc:date>2016-02-09T02:45:20+00:00</dc:date>
    <link>http://arxiv.org/abs/1602.01130</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper introduces a novel graph-analytic approach for detecting anomalies in network flow data called GraphPrints. Building on foundational network-mining techniques, our method represents time slices of traffic as a graph, then counts graphlets -- small induced subgraphs that describe local topology. By performing outlier detection on the sequence of graphlet counts, anomalous intervals of traffic are identified, and furthermore, individual IPs experiencing abnormal behavior are singled-out. Initial testing of GraphPrints is performed on real network data with an implanted anomaly. Evaluation shows false positive rates bounded by 2.84% at the time-interval level, and 0.05% at the IP-level with 100% true positive rates at both."

--- And how do you know how much the subgraph counts should fluctuate?]]></description>
<dc:subject>to:NB network_data_analysis re:network_differences statistics data_mining color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0d2c0cc1a9ec/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1507.08376">
    <title>[1507.08376] A Joint Graph Inference Case Study: the C.elegans Chemical and Electrical Connectomes</title>
    <dc:date>2015-08-06T00:18:38+00:00</dc:date>
    <link>http://arxiv.org/abs/1507.08376</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We investigate joint graph inference for the chemical and electrical connectomes of the \textit{Caenorhabditis elegans} roundworm. The \textit{C.elegans} connectomes consist of 253 non-isolated neurons with known functional attributes, and there are two types of synaptic connectomes, resulting in a pair of graphs. We formulate our joint graph inference from the perspectives of seeded graph matching and joint vertex classification. Our results suggest that connectomic inference should proceed in the joint space of the two connectomes, which has significant neuroscientific implications."]]></description>
<dc:subject>to:NB neuroscience network_data_analysis statistics re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:294a15edf530/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.cs.purdue.edu/homes/neville/papers/moreno-icdm2013.pdf">
    <title>Network Hypothesis Testing Using Mixed Kronecker Product Graph Models</title>
    <dc:date>2015-07-16T00:16:09+00:00</dc:date>
    <link>https://www.cs.purdue.edu/homes/neville/papers/moreno-icdm2013.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The recent interest in networks—social, physical, communication, information, etc.—has fueled a great deal of research on the analysis and modeling of graphs. However, many of the analyses have focused on a single large network (e.g., a subnetwork sampled from Facebook). Although several studies have compared networks from different domains or samples, they largely focus on empirical exploration of network similarities rather than explicit tests of hypotheses. This is in part due to a lack of statistical methods to determine whether two large networks are likely to have been drawn from the same underlying graph distribution. Research on across-network hypothesis testing methods has been limited by (i) difficulties associated with obtaining a set of networks to reason about the underlying graph distribution, and (ii) limitations of current statistical models of graphs that make it difficult to represent variations across networks. In this paper, we exploit the recent development of mixed-Kronecker Product Graph Models, which accurately capture the natural variation in real world graphs, to develop a model- based approach for hypothesis testing in networks."

--- I really should have known about this paper, and Jenn was remarkably graciously in telling me about it.]]></description>
<dc:subject>to_read network_data_analysis hypothesis_testing statistics neville.jennifer re:network_differences in_NB to_teach:graphons</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:69a71045b426/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neville.jennifer"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:graphons"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1506.08826">
    <title>[1506.08826] Statistical Inference using the Morse-Smale Complex</title>
    <dc:date>2015-07-14T09:42:40+00:00</dc:date>
    <link>http://arxiv.org/abs/1506.08826</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The Morse-Smale complex decomposes the sample space into cells where a given function f is increasing or decreasing. When applied to nonparametric density estimation and regression, it provides a way to represent, visualize and compare functions, even in high dimensions. In this paper, we study the estimation of the Morse-Smale complex and we use our results for a variety of statistical problems including: nonparametric two-sample testing, density estimation, nonparametric regression and mode clustering."]]></description>
<dc:subject>to:NB statistics nonparametrics re:network_differences wasserman.larry genovese.christopher chen.yen-chi kith_and_kin topology</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c801183db311/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wasserman.larry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:genovese.christopher"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:chen.yen-chi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:topology"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1506.00669">
    <title>[1506.00669] Concentration and regularization of random graphs</title>
    <dc:date>2015-06-03T15:14:14+00:00</dc:date>
    <link>http://arxiv.org/abs/1506.00669</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper studies how close random graphs are typically to their expectations. We interpret this question through the concentration of the adjacency and Laplacian matrices in the spectral norm. We study inhomogeneous Erd\"os-R\'enyi random graphs on n vertices, where edges form independently and possibly with different probabilities pij. Sparse random graphs whose expected degrees are o(logn) fail to concentrate. The obstruction is caused by vertices with abnormally high and low degrees. We show that concentration can be restored if we regularize the degrees of such vertices, and one can do this is various ways. As an example, let us reweight or remove enough edges to make all degrees bounded above by O(d) where d=maxpnij. Then we show that the resulting adjacency matrix A′ concentrates with the optimal rate: ∥A′−𝔼A∥=O(d‾‾√). Similarly, if we make all degrees bounded below by d by adding weight d/n to all edges, then the resulting Laplacian concentrates with the optimal rate: ∥L(A′)−L(𝔼A′)∥=O(1/d‾‾√). Our approach is based on Grothendieck-Pietsch factorization, using which we construct a new decomposition of random graphs. These results improve and simplify the recent work of L. Levina and the authors. We illustrate the concentration results with an application to the community detection problem in the analysis of networks."]]></description>
<dc:subject>to_read concentration_of_measure graph_theory graph_limits re:smoothing_adjacency_matrices re:network_differences in_NB via:mraginsky</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c32f3b03c787/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graph_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graph_limits"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:smoothing_adjacency_matrices"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:mraginsky"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.ncbi.nlm.nih.gov/pubmed/22008374">
    <title>Altered resting state complexity in schizophrenia. - PubMed - NCBI</title>
    <dc:date>2015-03-30T16:51:52+00:00</dc:date>
    <link>http://www.ncbi.nlm.nih.gov/pubmed/22008374</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The complexity of the human brain's activity and connectivity varies over temporal scales and is altered in disease states such as schizophrenia. Using a multi-level analysis of spontaneous low-frequency fMRI data stretching from the activity of individual brain regions to the coordinated connectivity pattern of the whole brain, we investigate the role of brain signal complexity in schizophrenia. Specifically, we quantitatively characterize the univariate wavelet entropy of regional activity, the bivariate pairwise functional connectivity between regions, and the multivariate network organization of connectivity patterns. Our results indicate that univariate measures of complexity are less sensitive to disease state than higher level bivariate and multivariate measures. While wavelet entropy is unaffected by disease state, the magnitude of pairwise functional connectivity is significantly decreased in schizophrenia and the variance is increased. Furthermore, by considering the network structure as a function of correlation strength, we find that network organization specifically of weak connections is strongly correlated with attention, memory, and negative symptom scores and displays potential as a clinical biomarker, providing up to 75% classification accuracy and 85% sensitivity. We also develop a general statistical framework for the testing of group differences in network properties, which is broadly applicable to studies where changes in network organization are crucial to the understanding of brain function."]]></description>
<dc:subject>to:NB complexity_measures functional_connectivity schizophrenia neuroscience network_data_analysis fmri re:network_differences bassett.danielle_s.</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:eca9200a964d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:complexity_measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_connectivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:schizophrenia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fmri"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bassett.danielle_s."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.pnas.org/content/112/10/2942.abstract.html">
    <title>On convex relaxation of graph isomorphism</title>
    <dc:date>2015-03-12T01:10:15+00:00</dc:date>
    <link>http://www.pnas.org/content/112/10/2942.abstract.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the problem of exact and inexact matching of weighted undirected graphs, in which a bijective correspondence is sought to minimize a quadratic weight disagreement. This computationally challenging problem is often relaxed as a convex quadratic program, in which the space of permutations is replaced by the space of doubly stochastic matrices. However, the applicability of such a relaxation is poorly understood. We define a broad class of friendly graphs characterized by an easily verifiable spectral property. We prove that for friendly graphs, the convex relaxation is guaranteed to find the exact isomorphism or certify its inexistence. This result is further extended to approximately isomorphic graphs, for which we develop an explicit bound on the amount of weight disagreement under which the relaxation is guaranteed to find the globally optimal approximate isomorphism. We also show that in many cases, the graph matching problem can be further harmlessly relaxed to a convex quadratic program with only n separable linear equality constraints, which is substantially more efficient than the standard relaxation involving 2n equality and n2 inequality constraints. Finally, we show that our results are still valid for unfriendly graphs if additional information in the form of seeds or attributes is allowed, with the latter satisfying an easy to verify spectral characteristic."]]></description>
<dc:subject>graph_theory computational_complexity optimization convexity network_data_analysis re:network_differences in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ba1653300c14/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graph_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computational_complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:convexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1502.07576">
    <title>[1502.07576] Comparison Issues in Large Graphs: State of the Art and Future Directions</title>
    <dc:date>2015-03-03T19:23:15+00:00</dc:date>
    <link>http://arxiv.org/abs/1502.07576</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Graph comparison is fundamentally important for many applications such as the analysis of social networks and biological data and has been a significant research area in the pattern recognition and pattern analysis domains. Nowadays, the graphs are large, they may have billions of nodes and edges. Comparison issues in such huge graphs are a challenging research problem. 
"In this paper, we survey the research advances of comparison problems in large graphs. We review graph comparison and pattern matching approaches that focus on large graphs. We categorize the existing approaches into three classes: partition-based approaches, search space based approaches and summary based approaches. All the existing algorithms in these approaches are described in detail and analyzed according to multiple metrics such as time complexity, type of graphs or comparison concept. Finally, we identify directions for future research."]]></description>
<dc:subject>network_data_analysis network_differences re:network_differences to_read via:vaguery in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:600e734dca88/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:vaguery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1409.2344">
    <title>[1409.2344] A nonparametric two-sample hypothesis testing problem for random dot product graphs</title>
    <dc:date>2015-01-20T13:33:07+00:00</dc:date>
    <link>http://arxiv.org/abs/1409.2344</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the problem of testing whether two finite-dimensional random dot product graphs have generating latent positions that are independently drawn from the same distribution, or distributions that are related via scaling or projection. We propose a test statistic that is a kernel-based function of the adjacency spectral embedding for each graph. We obtain a limiting distribution for our test statistic under the null and we show that our test procedure is consistent across a broad range of alternatives."]]></description>
<dc:subject>network_data_analysis hypothesis_testing two-sample_tests re:network_differences statistics to_read in_NB to_teach:graphons</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:041f7a5d64d9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:two-sample_tests"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:graphons"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1409.4317">
    <title>[1409.4317] Bootstrap-based testing for functional data</title>
    <dc:date>2015-01-20T04:19:47+00:00</dc:date>
    <link>http://arxiv.org/abs/1409.4317</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose a novel bootstrap-based methodology for testing hypotheses about equality of certain characteristics of the distributions between different populations in the context of functional data. The suggested testing methodology is simple and easy to implement. It resamples the original dataset in such a way that the null hypothesis of interest is satisfied and it can be potentially applied to a wide range of testing problems and test statistics of interest. Furthermore, it can be utilized to the case where more than two populations of functional data are considered. To illustrate it, we consider the important problems of testing the equality of mean functions or the equality of covariance functions (resp. covariance operators) between two populations. In this context, theoretical results that justify the validity of the suggested bootstrap-based procedure applied to some test statistics recently proposed in the literature, are established. Furthermore, simulation results demonstrate very good size and power performances in finite sample situations, including the case of testing problems and/or sample sizes where asymptotic considerations do not lead to satisfactory approximations. A real-life dataset analyzed in the literature is also examined."]]></description>
<dc:subject>to:NB functional_data_analysis hypothesis_testing bootstrap statistics re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:96e9a8c288f3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1405.3133">
    <title>[1405.3133] Graph Matching: Relax at Your Own Risk</title>
    <dc:date>2015-01-20T04:12:02+00:00</dc:date>
    <link>http://arxiv.org/abs/1405.3133</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Graph matching---aligning a pair of graphs to minimize their edge disagreements---has received wide-spread attention from both theoretical and applied communities over the past several decades, including combinatorics, computer vision, and connectomics. Its attention can be partially attributed to its computational difficulty. Although many heuristics have previously been proposed in the literature to approximately solve graph matching, very few have any theoretical support for their performance. A common technique is to relax the discrete problem to a continuous problem, therefore enabling practitioners to bring gradient-descent-type algorithms to bear. We prove that an indefinite relaxation (when solved exactly) almost always discovers the optimal permutation, while a common convex relaxation almost always fails to discover the optimal permutation. These theoretical results suggest that initializing the indefinite algorithm with the convex optimum might yield improved practical performance. Indeed, experimental results illuminate and corroborate these theoretical findings, demonstrating that excellent results are achieved in both benchmark and real data problems by amalgamating the two approaches."]]></description>
<dc:subject>graph_theory network_data_analysis optimization re:network_differences in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2937fbd143b8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graph_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1407.5525">
    <title>[1407.5525] Hypothesis Testing For Network Data in Functional Neuroimaging</title>
    <dc:date>2015-01-20T02:42:11+00:00</dc:date>
    <link>http://arxiv.org/abs/1407.5525</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In recent years, it has become common practice in neuroscience to use networks to summarize relational information in a set of measurements, typically assumed to be reflective of either functional or structural relationships between regions of interest in the brain. One of the most basic tasks of interest in the analysis of such data is the testing of hypotheses, in answer to questions such as "Is there a difference between the networks of these two groups of subjects?" In the classical setting, where the unit of interest is a scalar or a vector, such questions are answered through the use of familiar two-sample testing strategies. Networks, however, are not Euclidean objects, and hence classical methods do not directly apply. We address this challenge by drawing on concepts and techniques from geometry, and high-dimensional statistical inference. Our work is based on a precise geometric characterization of the space of graph Laplacian matrices and a nonparametric notion of averaging due to Fr\'echet. We motivate and illustrate our resulting methodologies for testing in the context of networks derived from functional neuroimaging data on human subjects from the 1000 Functional Connectomes Project. In particular, we show that this global test is more statistical powerful, than a mass-univariate approach."]]></description>
<dc:subject>to:NB to_read functional_connectivity fmri neuroscience network_data_analysis re:network_differences kolaczyk.eric</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7654ccf6898d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_connectivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fmri"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kolaczyk.eric"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1411.1350">
    <title>[1411.1350] Geometric Network Comparison</title>
    <dc:date>2015-01-19T21:13:17+00:00</dc:date>
    <link>http://arxiv.org/abs/1411.1350</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Network analysis has a crucial need for tools to compare networks and assess the significance of differences between networks. We propose a principled statistical approach to network comparison that approximates networks as probability distributions on negatively curved manifolds. We outline the theory, as well as implement the approach on simulated networks."]]></description>
<dc:subject>in_NB self-promotion network_differences re:network_differences statistics asta.dena kith_and_kin</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:713b3014c455/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:self-promotion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:asta.dena"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1411.1437">
    <title>[1411.1437] Higher Criticism: p-values and Criticism</title>
    <dc:date>2015-01-19T21:12:17+00:00</dc:date>
    <link>http://arxiv.org/abs/1411.1437</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper compares the higher criticism statistic (Donoho and Jin, 2004), a modification of the higher criticism statistic also suggested by Donoho and Jin, and two statistics of Berk-Jones (1979) type. New approximations to the significance levels of the statistics are derived, and their accuracy is studied by simulations. By numerical examples it is shown that over a broad range of sample sizes the Berk-Jones statistics have a better power function than the higher criticism statistics to detect sparse mixtures. The applications suggested by Meinshausen and Rice (2007), to find lower confidence bounds for the number of false hypotheses, and by Jeng, Cai, and Li (2012), to detect copy number variants, are also studied."]]></description>
<dc:subject>to:NB hypothesis_testing multiple_testing statistics re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cfbb55332a61/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:multiple_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.mitpressjournals.org/doi/abs/10.1162/NECO_a_00690">
    <title>Toward a Multisubject Analysis of Neural Connectivity</title>
    <dc:date>2014-12-29T02:04:33+00:00</dc:date>
    <link>http://www.mitpressjournals.org/doi/abs/10.1162/NECO_a_00690</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Directed acyclic graphs (DAGs) and associated probability models are widely used to model neural connectivity and communication channels. In many experiments, data are collected from multiple subjects whose connectivities may differ but are likely to share many features. In such circumstances, it is natural to leverage similarity among subjects to improve statistical efficiency. The first exact algorithm for estimation of multiple related DAGs was recently proposed by Oates, Smith, Mukherjee, and Cussens (2014). In this letter we present examples and discuss implications of the methodology as applied to the analysis of fMRI data from a multisubject experiment. Elicitation of tuning parameters requires care, and we illustrate how this may proceed retrospectively based on technical replicate data. In addition to joint learning of subject-specific connectivity, we allow for heterogeneous collections of subjects and simultaneously estimate relationships between the subjects themselves. This letter aims to highlight the potential for exact estimation in the multisubject setting."]]></description>
<dc:subject>to:NB graphical_models neuroscience functional_connectivity neural_data_analysis nichols.tom_e. re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2dc85589353c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_connectivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nichols.tom_e."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.pnas.org/content/111/49/E5321.abstract.html?etoc">
    <title>Network dynamics of the brain and influence of the epileptic seizure onset zone</title>
    <dc:date>2014-12-17T15:38:51+00:00</dc:date>
    <link>http://www.pnas.org/content/111/49/E5321.abstract.html?etoc</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The human brain is a dynamic networked system. Patients with partial epileptic seizures have focal regions that periodically diverge from normal brain network dynamics during seizures. We studied the evolution of brain connectivity before, during, and after seizures with graph-theoretic techniques on continuous electrocorticographic (ECoG) recordings (5.4 ± 1.7 d per patient, mean ± SD) from 12 patients with temporal, occipital, or frontal lobe partial onset seizures. Each electrode was considered a node in a graph, and edges between pairs of nodes were weighted by their coherence within a frequency band. The leading eigenvector of the connectivity matrix, which captures network structure, was tracked over time and clustered to uncover a finite set of brain network states. Across patients, we found that (i) the network connectivity is structured and defines a finite set of brain states, (ii) seizures are characterized by a consistent sequence of states, (iii) a subset of nodes is isolated from the network at seizure onset and becomes more connected with the network toward seizure termination, and (iv) the isolated nodes may identify the seizure onset zone with high specificity and sensitivity. To localize a seizure, clinicians visually inspect seizures recorded from multiple intracranial electrode contacts, a time-consuming process that may not always result in definitive localization. We show that network metrics computed from all ECoG channels capture the dynamics of the seizure onset zone as it diverges from normal overall network structure. This suggests that a state space model can be used to help localize the seizure onset zone in ECoG recordings."]]></description>
<dc:subject>to:NB functional_connectivity neural_data_analysis neuroscience network_data_analysis re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8bb76db78208/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_connectivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.pnas.org/content/111/46/E4997.abstract.html?etoc">
    <title>Decreased segregation of brain systems across the healthy adult lifespan</title>
    <dc:date>2014-11-22T03:21:14+00:00</dc:date>
    <link>http://www.pnas.org/content/111/46/E4997.abstract.html?etoc</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Healthy aging has been associated with decreased specialization in brain function. This characterization has focused largely on describing age-accompanied differences in specialization at the level of neurons and brain areas. We expand this work to describe systems-level differences in specialization in a healthy adult lifespan sample (n = 210; 20–89 y). A graph-theoretic framework is used to guide analysis of functional MRI resting-state data and describe systems-level differences in connectivity of individual brain networks. Young adults’ brain systems exhibit a balance of within- and between-system correlations that is characteristic of segregated and specialized organization. Increasing age is accompanied by decreasing segregation of brain systems. Compared with systems involved in the processing of sensory input and motor output, systems mediating “associative” operations exhibit a distinct pattern of reductions in segregation across the adult lifespan. Of particular importance, the magnitude of association system segregation is predictive of long-term memory function, independent of an individual’s age."]]></description>
<dc:subject>to:NB neuroscience functional_connectivity re:network_differences</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b47597ac4ae4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_connectivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.ms.unimelb.edu.au/~aurored/delaigle-hall-hc4.pdf">
    <title>Higher criticism in the context of unknown distribution, non-independence and classification</title>
    <dc:date>2014-10-18T01:57:19+00:00</dc:date>
    <link>http://www.ms.unimelb.edu.au/~aurored/delaigle-hall-hc4.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Higher criticism has been proposed as a tool for highly multiple hypothesis testing or signal detection, initially in cases where the distribution of a test statistic (or the noise in a signal) is known and the component tests are statisti- cally independent. In this paper we explore the extent to which the assumptions of known distribution and independence can be relaxed, and we consider too the ap- plication of higher criticism to classification. It is shown that effective distribution approximations can be achieved by using a threshold approach; that is, by disre- garding data components unless their significance level exceeds a sufficiently high value. This method exploits the good relative accuracy of approximations to light- tailed distributions. In particular, it can be effective when the true distribution is founded on something like a Studentised mean, or on an average of related type, which is commonly the case in practice. The issue of dependence among vector components is also shown not to be a serious difficulty in many circumstances."]]></description>
<dc:subject>to:NB have_skimmed multiple_testing statistics hall.peter hypothesis_testing statistical_inference_for_stochastic_processes re:network_differences to:blog</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:af36b1673db7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_skimmed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:multiple_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hall.peter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/math/0410072">
    <title>[math/0410072] Higher criticism for detecting sparse heterogeneous mixtures</title>
    <dc:date>2014-10-18T01:04:15+00:00</dc:date>
    <link>http://arxiv.org/abs/math/0410072</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Higher criticism, or second-level significance testing, is a multiple-comparisons concept mentioned in passing by Tukey. It concerns a situation where there are many independent tests of significance and one is interested in rejecting the joint null hypothesis. Tukey suggested comparing the fraction of observed significances at a given \alpha-level to the expected fraction under the joint null. In fact, he suggested standardizing the difference of the two quantities and forming a z-score; the resulting z-score tests the significance of the body of significance tests. We consider a generalization, where we maximize this z-score over a range of significance levels 0<\alpha\leq\alpha_0. 
"We are able to show that the resulting higher criticism statistic is effective at resolving a very subtle testing problem: testing whether n normal means are all zero versus the alternative that a small fraction is nonzero. The subtlety of this ``sparse normal means'' testing problem can be seen from work of Ingster and Jin, who studied such problems in great detail. In their studies, they identified an interesting range of cases where the small fraction of nonzero means is so small that the alternative hypothesis exhibits little noticeable effect on the distribution of the p-values either for the bulk of the tests or for the few most highly significant tests. 
"In this range, when the amplitude of nonzero means is calibrated with the fraction of nonzero means, the likelihood ratio test for a precisely specified alternative would still succeed in separating the two hypotheses."

--- It makes a lot more sense that the name would come from someone like Tukey.]]></description>
<dc:subject>to:NB multiple_testing hypothesis_testing empirical_processes statistics donoho.david jin.jiashun tukey.john_w. have_read re:network_differences to:blog</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1877e29a7c8c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:multiple_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:donoho.david"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:jin.jiashun"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:tukey.john_w."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1001.0591">
    <title>[1001.0591] Comparing Distributions and Shapes using the Kernel Distance</title>
    <dc:date>2014-10-16T15:15:28+00:00</dc:date>
    <link>http://arxiv.org/abs/1001.0591</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Starting with a similarity function between objects, it is possible to define a distance metric on pairs of objects, and more generally on probability distributions over them. These distance metrics have a deep basis in functional analysis, measure theory and geometric measure theory, and have a rich structure that includes an isometric embedding into a (possibly infinite dimensional) Hilbert space. They have recently been applied to numerous problems in machine learning and shape analysis. 
"In this paper, we provide the first algorithmic analysis of these distance metrics. Our main contributions are as follows: (i) We present fast approximation algorithms for computing the kernel distance between two point sets P and Q that runs in near-linear time in the size of (P cup Q) (note that an explicit calculation would take quadratic time). (ii) We present polynomial-time algorithms for approximately minimizing the kernel distance under rigid transformation; they run in time O(n + poly(1/epsilon, log n)). (iii) We provide several general techniques for reducing complex objects to convenient sparse representations (specifically to point sets or sets of points sets) which approximately preserve the kernel distance. In particular, this allows us to reduce problems of computing the kernel distance between various types of objects such as curves, surfaces, and distributions to computing the kernel distance between point sets. These take advantage of the reproducing kernel Hilbert space and a new relation linking binary range spaces to continuous range spaces with bounded fat-shattering dimension."]]></description>
<dc:subject>to:NB kernel_estimators two-sample_tests statistics probability re:network_differences have_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4ffff8f257a3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kernel_estimators"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:two-sample_tests"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>