GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning

TL;DR

This paper introduces GTCA, a hybrid GNN-Transformer architecture for graph contrastive learning that enhances representation quality and trustworthiness, addressing issues like over-smoothing and semantic disturbance.

Contribution

The paper proposes a novel GNN-Transformer cooperative architecture that combines the strengths of both models for more reliable and effective graph contrastive learning.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Theoretically verifies the trustworthiness of the proposed method.

Effectively mitigates over-smoothing and semantic disturbance issues.

Abstract

Graph contrastive learning (GCL) has become a hot topic in the field of graph representation learning. In contrast to traditional supervised learning relying on a large number of labels, GCL exploits augmentation strategies to generate multiple views and positive/negative pairs, both of which greatly influence the performance. Unfortunately, commonly used random augmentations may disturb the underlying semantics of graphs. Moreover, traditional GNNs, a type of widely employed encoders in GCL, are inevitably confronted with over-smoothing and over-squashing problems. To address these issues, we propose GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning (GTCA), which inherits the advantages of both GNN and Transformer, incorporating graph topology to obtain comprehensive graph representations. Theoretical analysis verifies the trustworthiness of the proposed method. Extensive experiments on benchmark datasets demonstrate state-of-the-art empirical performance.