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

, 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, )-based community detection method, but it imposes more constraints on the network reconstruction. More precisely, ), which considers the topology part always has more contribution if there is a mismatch, 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, provides higher normalized mutual information () values of 4.95%126.41% than the models without considering node content information on 13 out of 14 experimental networks. also presents higher values of 7.38%201.01% than on 13 out of 14 experimental networks. Moreover, shows good convergence performance, and it can converge after 100 iterations on all of the networks. also provides stability alike to similar methods in terms of the average standard deviation, which is 0.03 on all of the networks.