Dynamic Infinite Mixed-Membership Stochastic Blockmodel
This work addresses the need for more flexible and scalable models in social network analysis, though it appears incremental as it builds upon the existing Mixed-Membership Stochastic Blockmodel framework.
The paper tackles the problem of modeling dynamic social networks with potentially infinite communities and mixture memberships by proposing the Dynamic Infinite Mixed-Membership Stochastic Blockmodel (DIM3), which introduces parameters for persistence over time and demonstrates results using synthetic and real data.
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.