Str-GCL: Structural Commonsense Driven Graph Contrastive Learning

TL;DR

Str-GCL introduces a novel framework that explicitly incorporates structural commonsense into graph contrastive learning using first-order logic rules, significantly enhancing graph representations.

Contribution

It is the first to directly embed structural commonsense into GCL by leveraging logic rules and a representation alignment mechanism.

Findings

Outperforms existing GCL methods in experiments

Effectively captures structural commonsense in graph representations

Provides a new perspective on leveraging structural knowledge

Abstract

Graph Contrastive Learning (GCL) is a widely adopted approach in self-supervised graph representation learning, applying contrastive objectives to produce effective representations. However, current GCL methods primarily focus on capturing implicit semantic relationships, often overlooking the structural commonsense embedded within the graph's structure and attributes, which contains underlying knowledge crucial for effective representation learning. Due to the lack of explicit information and clear guidance in general graph, identifying and integrating such structural commonsense in GCL poses a significant challenge. To address this gap, we propose a novel framework called Structural Commonsense Unveiling in Graph Contrastive Learning (Str-GCL). Str-GCL leverages first-order logic rules to represent structural commonsense and explicitly integrates them into the GCL framework. It introduces topological and attribute-based rules without altering the original graph and employs a representation alignment mechanism to guide the encoder in effectively capturing this commonsense. To the best of our knowledge, this is the first attempt to directly incorporate structural commonsense into GCL. Extensive experiments demonstrate that Str-GCL outperforms existing GCL methods, providing a new perspective on leveraging structural commonsense in graph representation learning.