Community Discovery in Large-Scale Complex Networks Using Distributed SimRank Nonnegative Matrix Factorization

Abstract

Nonnegative Matrix Factorization (NMF) has become a powerful model for community discovery in complex networks. Existing NMF-based methods for community discovery often factorize the corresponding adjacent matrix of complex networks to obtain their community indicator matrices, which can provide intuitive interpretation for the community membership of nodes in complex networks. However, the adjacent matrix cannot represent the global structure feature of complex networks very well, and hence decreases the quality of discovered communities. Aiming at solving this problem, in this paper we investigate several representative similarity measures of graph nodes and propose an NMF-based method for community discovery using SimRank similarity measure. Additionally, to improve the scalability of our method, we implement its key components using MapReduce distributed computing framework, including computing SimRank feature matrix and iteratively solving the NMF-based model for community discovery. We conduct extensive experiments on several complex networks. The results show that our method can obtain better results of community discovery than NMF-based methods using other similarity measures. Moreover, our method presents good scalability and can be used to discover communities in the large-scale complex networks.