Combining Random Walks and Nonparametric Bayesian Topic Model for Community Detection
This addresses community detection for social network analysis, presenting a novel method but with incremental improvements over existing probabilistic models.
The paper tackles community detection in social networks by introducing RW-HDP, a probabilistic model combining random walks and Hierarchical Dirichlet Process, which automatically determines the number of communities and uses Stochastic Variational Inference for efficient inference.
Community detection has been an active research area for decades. Among all probabilistic models, Stochastic Block Model has been the most popular one. This paper introduces a novel probabilistic model: RW-HDP, based on random walks and Hierarchical Dirichlet Process, for community extraction. In RW-HDP, random walks conducted in a social network are treated as documents; nodes are treated as words. By using Hierarchical Dirichlet Process, a nonparametric Bayesian model, we are not only able to cluster nodes into different communities, but also determine the number of communities automatically. We use Stochastic Variational Inference for our model inference, which makes our method time efficient and can be easily extended to an online learning algorithm.