Improved Attributed Graph Clustering with Representation and Structure Augmentation

Jipeng Guo, Tengxiao Yin, Tianxiang Zhao, Jiayi Zhao, Yanfeng Sun, Junbin Gao, Youqing Wang

Abstract: Attributed graph clustering with auto-encoder (AE) and graph convolutional network (GCN) has achieved promising performance by fusing node attribute feature and structural graph information. However, there are some limitations: (i) structural information from pre-defined graph is inaccurate and insufficient for graph representation learning; (ii) graph embedding of last layer only contains partial information for clustering which inevitably deteriorates clustering performance. To address these issues, we propose the Improved Attributed Graph Clustering method with Representation and Structure Augmentation (IAGC-RSA). The representation augmentor with multi-scale and multi-source representation attention fusion and structure augmentor with adaptive graph learning are designed for information augmentation from structure level and feature level. Thus, IAGC-RSA could learn a more comprehensive and discriminative graph embedding representation for subsequent clustering task. Experimental results conducted on some benchmark datasets demonstrate the effectiveness of IAGC-RSA for node clustering task.