期刊
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
卷 8, 期 1, 页码 463-476出版社
IEEE COMPUTER SOC
DOI: 10.1109/TNSE.2020.3040407
关键词
Detectors; Symmetric matrices; Image edge detection; Social networking (online); Topology; Measurement; Knowledge engineering; Computational Intelligence; Social Network; Network Representation; Community Detection; Pointwise Mutual Information; Symmetric and Non-negative Matrix Factorization; Graph-regularization
资金
- National Natural Science Foundation of China [61772493]
- Natural Science Foundation of Chongqing (China) [cstc2019jcyjjqX0013, cstc2019jcyj-msxmX0578]
- Natural Science Foundation of Zhejiang Province [LR20F020002]
- Pioneer Hundred Talents Program of Chinese Academy of Sciences
The proposed PGS model combines Pointwise Mutual Information and graph regularization in Symmetric and Non-negative Matrix Factorization to quantify implicit associations among nodes, achieve precise representation of local topology, and implement efficient community detection. Empirical studies show that PGS model outperforms state-of-the-art community detectors in accuracy gain for community detection in real-world social networks.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据