GCL-GCN: Graphormer and Contrastive Learning Enhanced Attributed Graph Clustering Network

TL;DR

GCL-GCN is a novel attributed graph clustering model that combines Graphormer and contrastive learning to improve node representation quality, especially in complex, sparse, and heterogeneous graph data.

Contribution

It introduces a Graphormer module with centrality and spatial encoding and a contrastive learning module, enhancing local dependency capture and feature discriminability.

Findings

Outperforms 14 state-of-the-art methods in clustering quality and robustness.

Achieves significant improvements on the Cora dataset in ACC, NMI, and ARI.

Demonstrates effectiveness across six diverse datasets.

Abstract

Attributed graph clustering holds significant importance in modern data analysis. However, due to the complexity of graph data and the heterogeneity of node attributes, leveraging graph information for clustering remains challenging. To address this, we propose a novel deep graph clustering model, GCL-GCN, specifically designed to address the limitations of existing models in capturing local dependencies and complex structures when dealing with sparse and heterogeneous graph data. GCL-GCN introduces an innovative Graphormer module that combines centrality encoding and spatial relationships, effectively capturing both global and local information between nodes, thereby enhancing the quality of node representations. Additionally, we propose a novel contrastive learning module that significantly enhances the discriminative power of feature representations. In the pre-training phase, this module increases feature distinction through contrastive learning on the original feature matrix, ensuring more identifiable initial representations for subsequent graph convolution and clustering tasks. Extensive experimental results on six datasets demonstrate that GCL-GCN outperforms 14 advanced methods in terms of clustering quality and robustness. Specifically, on the Cora dataset, it improves ACC, NMI, and ARI by 4.94%, 13.01%, and 10.97%, respectively, compared to the primary comparison method MBN.