A Multi-View Clustering Method for Community Discovery Integrating Links and Tags

Abstract

Community discovery is a popular research problem in the realm of complex network analysis and many methods have been proposed to solve it. However, most of the existing methods only consider the usage of links information and ignore tags information of complex networks. As a result, the quality of their discovered communities is often poor owing to the sparse and noisy data existing in links information. Actually, both links and tags contain noisy but complementary information with each other. In this paper, we propose a multi-view clustering method for community discovery, which is based on multi-view Nonnegative Matrix Factorization (NMF) model and can provide a unified framework to integrate links and tags information. Its key idea is to build a joint NMF process with the constraint that pushes community indicator matrices of links view and tags view towards a common consensus matrix, which can uncover the common latent community structure shared by links view and tags view. Under the optimization framework of multiplicative update rules, we devise the corresponding community discovery algorithm, which can be used to obtain higher quality communities. We conduct extensive experiments on several real datasets and the results demonstrate the effectiveness of our method.