Mixed Membership Stochastic Blockmodels
TLDR
In this article, the authors introduce a class of variance allocation models for pairwise measurements, called mixed membership stochastic blockmodels, which combine global parameters that instantiate dense patches of connectivity (blockmodel) with local parameters (mixed membership), and develop a general variational inference algorithm for fast approximate posterior inference.Abstract:
Consider data consisting of pairwise measurements, such as presence or absence of links between pairs of objects. These data arise, for instance, in the analysis of protein interactions and gene regulatory networks, collections of author-recipient email, and social networks. Analyzing pairwise measurements with probabilistic models requires special assumptions, since the usual independence or exchangeability assumptions no longer hold. Here we introduce a class of variance allocation models for pairwise measurements: mixed membership stochastic blockmodels. These models combine global parameters that instantiate dense patches of connectivity (blockmodel) with local parameters that instantiate node-specific variability in the connections (mixed membership). We develop a general variational inference algorithm for fast approximate posterior inference. We demonstrate the advantages of mixed membership stochastic blockmodels with applications to social networks and protein interaction networks.read more
Citations
More filters
Journal ArticleDOI
Reconceptualizing the classification of PNAS articles
Edoardo M. Airoldi,Elena A. Erosheva,Stephen E. Fienberg,Cyrille Joutard,Tanzy Love,Suyash Shringarpure +5 more
TL;DR: This work reevaluate PNAS article classification using latent pattern models from statistical machine learning that identify semantic structure in co-occurrence of words in the abstracts and references that suggest ways to reconceptualize the organization of papers published in PNAS.
Posted Content
A new SVD approach to optimal topic estimation
Zheng Tracy Ke,Minzhe Wang +1 more
TL;DR: The method has a faster rate of convergence than existing methods in a wide variety of cases and achieves the optimal rate for cases where documents are long or $n is much larger than $p, and there is a clear simplex structure associated with the SVD of the data matrices, which largely validates the discovery.
MonographDOI
Topics at the Frontier of Statistics and Network Analysis: (Re)Visiting the Foundations
TL;DR: A snapshot of the current frontier of statistics and network analysis focusing on the foundational topics of modeling, sampling, and design is provided in this article, where the emphasis is not only on what has been done, but on what remains to be done.
Journal ArticleDOI
Estimating identification disclosure risk using mixed membership models
TL;DR: A Bayesian GoM model for multinomial variables and a Markov chain Monte Carlo algorithm for fitting the model are presented and it is shown that GoM models provide more accurate estimates of the total number of uniques in the samples and offer record-level predictions of uniqueness that dominate those based on log-linear models.
Proceedings Article
Bayesian Poisson tucker decomposition for learning the structure of international relations
TL;DR: In this article, the authors introduce Bayesian Poisson Tucker decomposition (BPTD) for modeling country-country interaction event data, which consists of interaction events of the form "country i took action a toward country j at time t".
References
More filters
Journal ArticleDOI
Maximum likelihood from incomplete data via the EM algorithm
Journal ArticleDOI
Gene Ontology: tool for the unification of biology
M Ashburner,Catherine A. Ball,Judith A. Blake,David Botstein,Heather Butler,J. M. Cherry,Allan Peter Davis,Kara Dolinski,Selina S. Dwight,J.T. Eppig,Midori A. Harris,David P. Hill,Laurie Issel-Tarver,Andrew Kasarskis,Suzanna E. Lewis,John C. Matese,Joel E. Richardson,M. Ringwald,Gerald M. Rubin,Gavin Sherlock +19 more
TL;DR: The goal of the Gene Ontology Consortium is to produce a dynamic, controlled vocabulary that can be applied to all eukaryotes even as knowledge of gene and protein roles in cells is accumulating and changing.
Journal ArticleDOI
Latent dirichlet allocation
TL;DR: This work proposes a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hofmann's aspect model.
Journal ArticleDOI
Finding scientific topics
TL;DR: A generative model for documents is described, introduced by Blei, Ng, and Jordan, and a Markov chain Monte Carlo algorithm is presented for inference in this model, which is used to analyze abstracts from PNAS by using Bayesian model selection to establish the number of topics.
Journal ArticleDOI
Functional organization of the yeast proteome by systematic analysis of protein complexes
Anne-Claude Gavin,Markus Bösche,Roland Krause,Paola Grandi,Martina Marzioch,Andreas Bauer,Jörg Schultz,Jens Rick,Anne-Marie Michon,Cristina-Maria Cruciat,Marita Remor,Christian Höfert,Malgorzata Schelder,Miro Brajenovic,Heinz Ruffner,Alejandro Merino,Karin Klein,Manuela Hudak,David Dickson,Tatjana Rudi,Volker Gnau,Angela Bauch,Sonja Bastuck,Bettina Huhse,Christina Leutwein,Marie-Anne Heurtier,Richard R. Copley,Angela Edelmann,Erich Querfurth,Vladimir Rybin,Gerard Drewes,Manfred Raida,Tewis Bouwmeester,Peer Bork,Bertrand Séraphin,Bernhard Kuster,Gitte Neubauer,Giulio Superti-Furga +37 more
TL;DR: The analysis provides an outline of the eukaryotic proteome as a network of protein complexes at a level of organization beyond binary interactions, which contains fundamental biological information and offers the context for a more reasoned and informed approach to drug discovery.