The trade-off between topology and content in community detection: An adaptive encoder–decoder-based NMF approach

• Published in: Expert systems with applications Vol. 209; p. 118230
• Main Authors: Zhao, Zhili, Ke, Zhengyou, Gou, Zhuoyue, Guo, Hao, Jiang, Kunyuan, Zhang, Ruisheng
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.12.2022
• Subjects: Community detection; Encoder–decoder; Network topology; Node attributes; Non-negative matrix factorization; Encoder–decoder; Community detection; Node attributes; Network topology; Non-negative matrix factorization
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2022.118230

Community detection is an important research field of complex network analysis and focuses on the study of networks’ aggregation behaviours. Different from traditional methods that only consider network structural topology, many efforts have been put into combining network structural topology with node content attributes to achieve better community detection performance. However, it is critical to make an appropriate trade-off between structural topology and node content. In this paper, we propose an adaptive trade-off approach, called ANMF, which not only considers both structural topology and node content, but also provides a flexible parameter to balance their contribution. Compared with other related approaches, ANMF is a kind of non-negative matrix factorization (NMF)-based community detection method, but it imposes more constraints on the network reconstruction. More precisely, ANMF simultaneously employs a decoder that reconstructs a network from its community membership space and an encoder that transforms the network into the community membership space. Moreover, compared with the most related state-of-the-art effort adaptive semantic community detection (ASCD), which considers the topology part always has more contribution if there is a mismatch, ANMF considers the mismatch in two different situations, i.e., the topology part contributes more than the node content part and the node content part contributes more than the topology part. Based on the intensive evaluation on both real and artificial networks, ANMF provides higher normalized mutual information (NMI) values of 4.95%∼126.41% than the models without considering node content information on 13 out of 14 experimental networks. ANMF also presents higher NMI values of 7.38%∼201.01% than ASCD on 13 out of 14 experimental networks. Moreover, ANMF shows good convergence performance, and it can converge after 100 iterations on all of the networks. ANMF also provides stability alike to similar methods in terms of the average NMI standard deviation, which is 0.03 on all of the networks. •ANMF is a novel community detection method based on balancing topology and content.•ANMF imposes more constraints by using a decoder and an encoder simultaneously.•ANMF considers two different mismatches between topology and content.•ANMF presents better performance over the most related state-of-the-art efforts.•ANMF shows good convergence performance and stability alike to similar method.