Highly-Accurate Community Detection via Pointwise Mutual Information-Incorporated Symmetric Non-Negative Matrix Factorization

• Published in: IEEE transactions on network science and engineering Vol. 8; no. 1; pp. 463 - 476
• Main Authors: Luo, Xin, Liu, Zhigang, Shang, Mingsheng, Lou, Jungang, Zhou, MengChu
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Community Detection; Computational Intelligence; Detectors; Empirical analysis; Factorization; Graph-regularization; Image edge detection; Industrial applications; Knowledge engineering; Mathematical analysis; Matrix methods; Measurement; Model accuracy; Network analysis; Network Representation; Nodes; Pointwise Mutual Information; Regularization; Social Network; Social networking (online); Social networks; Symmetric and Non-negative Matrix Factorization; Symmetric matrices; Topology
• ISSN: 2327-4697; 2334-329X
• DOI: 10.1109/TNSE.2020.3040407

Community detection, aiming at determining correct affiliation of each node in a network, is a critical task of complex network analysis. Owing to its high efficiency, Symmetric and Non-negative Matrix Factorization (SNMF) is frequently adopted to handle this task. However, existing SNMF models mostly focus on a network's first-order topological information described by its adjacency matrix without considering the implicit associations among involved nodes. To address this issue, this study proposes a Pointwise mutual information-incorporated and Graph-regularized SNMF (PGS) model. It uses a) Pointwise Mutual Information to quantify implicit associations among nodes, thereby completing the missing but crucial information among critical nodes in a uniform way; b) graph-regularization to achieve precise representation of local topology, and c) SNMF to implement efficient community detection. Empirical studies on eight real-world social networks generated by industrial applications demonstrate that a PGS model achieves significantly higher accuracy gain in community detection than state-of-the-art community detectors.