Community Detection Algorithm Combining Stochastic Block Model and Attribute Data Clustering

TL;DR

This paper introduces a novel community detection algorithm that combines network structure and vertex attribute data using a Bayesian framework, belief propagation, and an EM algorithm, validated on synthetic and real networks.

Contribution

It presents a new method integrating attribute data with network structure for community detection, enhancing accuracy over existing approaches.

Findings

Effective in detecting communities in synthetic networks

Successfully applied to real-world network data

Outperforms traditional structure-only methods

Abstract

We propose a new algorithm to detect the community structure in a network that utilizes both the network structure and vertex attribute data. Suppose we have the network structure together with the vertex attribute data, that is, the information assigned to each vertex associated with the community to which it belongs. The problem addressed this paper is the detection of the community structure from the information of both the network structure and the vertex attribute data. Our approach is based on the Bayesian approach that models the posterior probability distribution of the community labels. The detection of the community structure in our method is achieved by using belief propagation and an EM algorithm. We numerically verified the performance of our method using computer-generated networks and real-world networks.