Model Selection in Overlapping Stochastic Block Models

TL;DR

This paper introduces a Bayesian model selection criterion for Overlapping Stochastic Block Models, enabling effective determination of the number of classes in network clustering, validated through simulations and real data.

Contribution

It develops a new Bayesian criterion with a variational Bayes EM algorithm for selecting the number of classes in overlapping stochastic block models.

Findings

The criterion accurately identifies the number of classes in simulated data.

The method performs well on real network data.

It improves model selection over existing approaches.

Abstract

Networks are a commonly used mathematical model to describe the rich set of interactions between objects of interest. Many clustering methods have been developed in order to partition such structures, among which several rely on underlying probabilistic models, typically mixture models. The relevant hidden structure may however show overlapping groups in several applications. The Overlapping Stochastic Block Model (2011) has been developed to take this phenomenon into account. Nevertheless, the problem of the choice of the number of classes in the inference step is still open. To tackle this issue, we consider the proposed model in a Bayesian framework and develop a new criterion based on a non asymptotic approximation of the marginal log-likelihood. We describe how the criterion can be computed through a variational Bayes EM algorithm, and demonstrate its efficiency by running it on both simulated and real data.