Robust Graph Convolutional Clustering With Adaptive Graph Learning

Abstract

Graph-based clustering learns underlying data representation by employing topological graph structure. Recently, Graph Convolutional Network (GCN)-based clustering methods have accumulated great attentions and achieved great performance. Its performance is seriously determined by the quality of pre-provided graph, which is usually constructed by predefined model (such as k-Nearest-Neighbor). However, the graph may be inaccurate due to the noises and fixed graph limits flexibility of model learning. In this paper, we propose a Robust Graph Convolutional Clustering (RGCC) method, which adaptively learns a clean and accurate graph from original graph. Specifically, adaptive graph with low-rank and sparse structures be learned during the optimization process, which can better encode structural information of data than fixed graph. Then, to explore the local connectivity of data, graph Laplacian constraint is introduced. Thus, optimal graph relationships and discriminative representation of data could be simultaneously learned, which improves the flexibility of the RGCC model. By designing a self-supervised clustering module, it can self-supervise the node representations learning and thus explore the better clustering structure. Experimental results on several benchmark databases reveal the superiority of the proposed RGCC approach.