Clustering holds profound significance in data mining. In recent years, graph convolutional network (GCN) has emerged as a powerful tool for deep clustering, integrating both graph structural information and node attributes. However, most existing methods ignore the higher-order structural information of the graph. Evidently, nodes within the same cluster can establish distant connections. Besides, recent deep clustering methods usually apply a self-supervised module to monitor the training process of their model, focusing solely on node attributes without paying attention to graph structure. In this paper, we propose a novel graph clustering network to make full use of graph structural information. To capture the higher-order structural information, we design a graph mutual infomax module, effectively maximizing mutual information between graph-level and node-level representations, and employ a trinary self-supervised module that includes modularity as a structural constraint. Our proposed model outperforms many state-of-the-art methods on various datasets, demonstrating its superiority.

提出了一种新颖的图聚类网络，能充分利用图结构信息，捕获高阶结构信息，并应用三元自监督模块作为结构约束，在多个数据集上优于多个最先进的方法，显示出其优越性。

融合高阶结构信息的图聚类