A generalized stochastic block model for overlapping community detection

Abstract

Over the past two decades, community detection has been extensively explored. Yet, the challenge of identifying overlapping communities remains unresolved. In this letter, we introduces a novel approach called the generalized stochastic block model, which addresses this issue by allowing nodes to belong to multiple communities. This approach extends the traditional representation of nodal community assignment from a single community label to a label vector, with each element indicating the membership of a node in a specific community. To tackle this model, we develop a Markov Chain Monte Carlo algorithm. Through numerical experiments conducted on synthetic and empirical networks, we demonstrate the efficacy of our proposed framework in accurately detecting overlapping communities.