Parallel Particle Swarm Optimization for Community Detection in Large-Scale Networks

Abstract

Community detection has great applications in many areas. Many algorithms have been proposed to solve this problem, while these algorithms could not detect communities in large-scale networks effectively and efficiently. In this paper, a parallel particle swarm optimization algorithm based on Apache Spark for community detection is put forward. In this algorithm, an effective representation and a specific updating strategy of discrete particle swarm optimization for parallel computing are designed. Modularity density is used as the objective function and GraphX is used to optimize modularity density parallel. To demonstrate the effectiveness of the proposed algorithm, various experiments on small real-world networks with ground-truth communities are carried out. At the same time, we test the performance of the proposed algorithm on large-scale networks. The experimental results indicate that the proposed method is effective and suitable for community detection in large-scale networks.