Contrastive Deep Nonnegative Matrix Factorization for Community Detection
Yuecheng Li, Jialong Chen, Chuan Chen, Lei Yang, Zibin Zheng
TL;DR
CDNMF tackles limitations of traditional NMF-based community detection by enabling hierarchical, multi-view representations that incorporate node attributes. It combines a deep NMF backbone with graph regularization and integrates a graph-contrastive learning framework across topology and attributes, aided by a debiased negative sampling layer. The method jointly optimizes DNMF reconstruction, graph regularization, and a contrastive loss, predicting community membership via c_i^* = argmax(V_p(:, i)). Experiments on Cora, Citeseer, and PubMed show CDNMF consistently outperforms state-of-the-art methods on ACC and NMI, validating the effectiveness of multi-view, deep factorization for interpretable and robust community detection, with potential for extending to other matrix-factorization and contrastive-learning paradigms.
Abstract
Recently, nonnegative matrix factorization (NMF) has been widely adopted for community detection, because of its better interpretability. However, the existing NMF-based methods have the following three problems: 1) they directly transform the original network into community membership space, so it is difficult for them to capture the hierarchical information; 2) they often only pay attention to the topology of the network and ignore its node attributes; 3) it is hard for them to learn the global structure information necessary for community detection. Therefore, we propose a new community detection algorithm, named Contrastive Deep Nonnegative Matrix Factorization (CDNMF). Firstly, we deepen NMF to strengthen its capacity for information extraction. Subsequently, inspired by contrastive learning, our algorithm creatively constructs network topology and node attributes as two contrasting views. Furthermore, we utilize a debiased negative sampling layer and learn node similarity at the community level, thereby enhancing the suitability of our model for community detection. We conduct experiments on three public real graph datasets and the proposed model has achieved better results than state-of-the-art methods. Code available at https://github.com/6lyc/CDNMF.git.