Quantum inspired genetic algorithm for community structure detection in social networks

Abstract

Community detection is a key problem in social network analysis. We propose a two-phase algorithm for detecting community structure in social networks. First phase employs a local-search method to group together nodes that have a high chance of falling in a single community. The second phase is bi-partitioning strategy that optimizes network modularity and deploys a variant of quantum-inspired genetic algorithm. The proposed algorithm does not require any knowledge of the number of communities beforehand and works well for both directed and undirected networks. Experiments on synthetic and real-life networks show that the method is able to successfully reveal community structure with high modularity.