Deep Graph Clustering via Dual Correlation Reduction

TL;DR

This paper introduces DCRN, a self-supervised deep graph clustering method that reduces dual-level information correlation to prevent representation collapse and improve clustering accuracy.

Contribution

The paper proposes a novel dual correlation reduction approach with a siamese network and a propagation regularization to enhance discriminative features in graph clustering.

Findings

Outperforms state-of-the-art methods on six benchmark datasets.

Effectively prevents representation collapse and over-smoothing.

Improves discriminative capability of node representations.

Abstract

Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different groups, has attracted intensive attention in recent years. However, we observe that, in the process of node encoding, existing methods suffer from representation collapse which tends to map all data into the same representation. Consequently, the discriminative capability of the node representation is limited, leading to unsatisfied clustering performance. To address this issue, we propose a novel self-supervised deep graph clustering method termed Dual Correlation Reduction Network (DCRN) by reducing information correlation in a dual manner. Specifically, in our method, we first design a siamese network to encode samples. Then by forcing the cross-view sample correlation matrix and cross-view feature correlation matrix to approximate two identity matrices, respectively, we reduce the information correlation in the dual-level, thus improving the discriminative capability of the resulting features. Moreover, in order to alleviate representation collapse caused by over-smoothing in GCN, we introduce a propagation regularization term to enable the network to gain long-distance information with the shallow network structure. Extensive experimental results on six benchmark datasets demonstrate the effectiveness of the proposed DCRN against the existing state-of-the-art methods.