Cross-View Graph Consistency Learning for Invariant Graph Representations

TL;DR

This paper introduces a novel cross-view graph consistency learning method that enhances invariant graph representations for link prediction by using complementary augmentations and a cross-view training scheme, backed by theoretical analysis and empirical validation.

Contribution

The paper proposes a new CGCL approach with a coupled augmentation scheme and cross-view training, improving invariant graph representation learning for link prediction.

Findings

Achieves competitive results on benchmark graph datasets.

Effectively mitigates information loss during data augmentation.

Provides comprehensive theoretical analysis of CGCL.

Abstract

Graph representation learning is fundamental for analyzing graph-structured data. Exploring invariant graph representations remains a challenge for most existing graph representation learning methods. In this paper, we propose a cross-view graph consistency learning (CGCL) method that learns invariant graph representations for link prediction. First, two complementary augmented views are derived from an incomplete graph structure through a coupled graph structure augmentation scheme. This augmentation scheme mitigates the potential information loss that is commonly associated with various data augmentation techniques involving raw graph data, such as edge perturbation, node removal, and attribute masking. Second, we propose a CGCL model that can learn invariant graph representations. A cross-view training scheme is proposed to train the proposed CGCL model. This scheme attempts to maximize the consistency information between one augmented view and the graph structure reconstructed from the other augmented view. Furthermore, we offer a comprehensive theoretical CGCL analysis. This paper empirically and experimentally demonstrates the effectiveness of the proposed CGCL method, achieving competitive results on graph datasets in comparisons with several state-of-the-art algorithms.