Dynamic Infinite Mixed-Membership Stochastic Blockmodel

TL;DR

This paper introduces DIM3, a dynamic, infinite-community mixed-membership stochastic blockmodel that captures evolving social network structures with persistent community memberships over time.

Contribution

It extends MMSB to an infinite, dynamic setting with new parameters for membership persistence, and provides effective sampling strategies for inference.

Findings

Successful application to synthetic data

Effective posterior sampling methods demonstrated

Model captures temporal community dynamics

Abstract

Directional and pairwise measurements are often used to model inter-relationships in a social network setting. The Mixed-Membership Stochastic Blockmodel (MMSB) was a seminal work in this area, and many of its capabilities were extended since then. In this paper, we propose the \emph{Dynamic Infinite Mixed-Membership stochastic blockModel (DIM3)}, a generalised framework that extends the existing work to a potentially infinite number of communities and mixture memberships for each of the network's nodes. This model is in a dynamic setting, where additional model parameters are introduced to reflect the degree of persistence between one's memberships at consecutive times. Accordingly, two effective posterior sampling strategies and their results are presented using both synthetic and real data.