“…In the past few decades, various community detection methods have emerged, including methods based on graph partitioning [7,8], methods based on spectral clustering [9], methods based on modularity optimization [10], methods based on The technique of label propagation [11,12] and the way based on deep learning [13]. It is worth pointing out that non-negative matrix factorization (NMF) is also widely used in community discovery due to its simplicity, easy scalability, and strong interpretability [14]. At present, many community discovery methods based on NMF have been proposed, for example, the community method based on naive non-negative matrix factorization [15], the community discovery method SNMF based on symmetric NMF [16], the community discovery method SNMF-SS [17] based on semi-supervised NMF, NMF community discovery method based on node similarity and modularity M-NMF [18] and so on.…”