Skip to main content

Modeling Overlapping Communities with Node Popularities

Author(s): Gopalan, Prem K; Wang, Chong; Blei, David

To refer to this page use:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGopalan, Prem K-
dc.contributor.authorWang, Chong-
dc.contributor.authorBlei, David-
dc.identifier.citationGopalan, Prem, Chong Wang, and David M. Blei. "Modeling Overlapping Communities with Node Popularities." In Advances in Neural Information Processing Systems 26 (2013): pp. 2850-2858.en_US
dc.description.abstractWe develop a probabilistic approach for accurate network modeling using node popularities within the framework of the mixed-membership stochastic blockmodel (MMSB). Our model integrates two basic properties of nodes in social networks: homophily and preferential connection to popular nodes. We develop a scalable algorithm for posterior inference, based on a novel nonconjugate variant of stochastic variational inference. We evaluate the link prediction accuracy of our algorithm on nine real-world networks with up to 60,000 nodes, and on simulated networks with degree distributions that follow a power law. We demonstrate that the AMP predicts significantly better than the MMSB.en_US
dc.format.extent2850 - 2858en_US
dc.relation.ispartofAdvances in Neural Information Processing Systemsen_US
dc.rightsFinal published version. Article is made available in OAR by the publisher's permission or policy.en_US
dc.titleModeling Overlapping Communities with Node Popularitiesen_US
dc.typeConference Articleen_US

Files in This Item:
File Description SizeFormat 
ModelOverlapCommunitiesNodePopularities.pdf1.35 MBAdobe PDFView/Download

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.