Open access
Jul 2026
Constrained deep nonnegative matrix factorization with graph convolutional networks for unsupervised community detection
GCNCDNMF, a framework that integrates graph convolutional networks (GCNs) with a constrained deep nonnegative matrix factorization (CDNMF) module, which consistently outperforms state-of-the-art methods in accuracy, normalized mutual information, and adjusted Rand index.
Shunli Li, Ling Wang, Mingjun Bai
· Journal of King Saud Univers... · 0 citations