Mixed Membership Stochastic Blockmodels.

TLDR

Observations of pairwise relationships arise in diverse domains such as protein interactions, gene regulatory networks, email exchanges, and social networks, where standard probabilistic models struggle because exchangeability assumptions break down. The authors propose the mixed membership stochastic blockmodel to capture mixed membership latent relational structure in relational data. The model extends traditional blockmodels by allowing each object to have mixed membership across latent groups, and the authors develop a fast variational inference algorithm and demonstrate its use on social and protein interaction networks.

Abstract

Observations consisting of measurements on relationships for pairs of objects arise in many settings, such as protein interaction and gene regulatory networks, collections of author-recipient email, and social networks. Analyzing such data with probabilisic models can be delicate because the simple exchangeability assumptions underlying many boilerplate models no longer hold. In this paper, we describe a latent variable model of such data called the mixed membership stochastic blockmodel. This model extends blockmodels for relational data to ones which capture mixed membership latent relational structure, thus providing an object-specific low-dimensional representation. We develop a general variational inference algorithm for fast approximate posterior inference. We explore applications to social and protein interaction networks.