Redundancy-Free Self-Supervised Relational Learning for Graph Clustering

TL;DR

This paper introduces R²FGC, a self-supervised graph clustering method that leverages relational information at multiple levels to improve clustering accuracy by reducing redundancy and preserving semantic relations.

Contribution

It proposes a novel relational redundancy-free approach combining attribute and structure information with autoencoders for improved graph clustering.

Findings

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

Effectively reduces relational redundancy in learned embeddings

Alleviates over-smoothing in deep graph models

Abstract

Graph clustering, which learns the node representations for effective cluster assignments, is a fundamental yet challenging task in data analysis and has received considerable attention accompanied by graph neural networks in recent years. However, most existing methods overlook the inherent relational information among the non-independent and non-identically distributed nodes in a graph. Due to the lack of exploration of relational attributes, the semantic information of the graph-structured data fails to be fully exploited which leads to poor clustering performance. In this paper, we propose a novel self-supervised deep graph clustering method named Relational Redundancy-Free Graph Clustering (R$^2$FGC) to tackle the problem. It extracts the attribute- and structure-level relational information from both global and local views based on an autoencoder and a graph autoencoder. To obtain effective representations of the semantic information, we preserve the consistent relation among augmented nodes, whereas the redundant relation is further reduced for learning discriminative embeddings. In addition, a simple yet valid strategy is utilized to alleviate the over-smoothing issue. Extensive experiments are performed on widely used benchmark datasets to validate the superiority of our R$^2$FGC over state-of-the-art baselines. Our codes are available at https://github.com/yisiyu95/R2FGC.