Self-Reinforced Graph Contrastive Learning

TL;DR

SRGCL introduces a self-reinforcing framework for graph contrastive learning that dynamically selects high-quality positive pairs using the model's own encoder, leading to improved graph representations across multiple tasks.

Contribution

It proposes a novel self-reinforced positive pair selection mechanism in graph contrastive learning, enhancing the quality of learned representations.

Findings

Outperforms state-of-the-art GCL methods on diverse tasks

Effectively maintains graph structure during contrastive learning

Demonstrates robustness across various domains

Abstract

Graphs serve as versatile data structures in numerous real-world domains-including social networks, molecular biology, and knowledge graphs-by capturing intricate relational information among entities. Among graph-based learning techniques, Graph Contrastive Learning (GCL) has gained significant attention for its ability to derive robust, self-supervised graph representations through the contrasting of positive and negative sample pairs. However, a critical challenge lies in ensuring high-quality positive pairs so that the intrinsic semantic and structural properties of the original graph are preserved rather than distorted. To address this issue, we propose SRGCL (Self-Reinforced Graph Contrastive Learning), a novel framework that leverages the model's own encoder to dynamically evaluate and select high-quality positive pairs. We designed a unified positive pair generator employing multiple augmentation strategies, and a selector guided by the manifold hypothesis to maintain the underlying geometry of the latent space. By adopting a probabilistic mechanism for selecting positive pairs, SRGCL iteratively refines its assessment of pair quality as the encoder's representational power improves. Extensive experiments on diverse graph-level classification tasks demonstrate that SRGCL, as a plug-in module, consistently outperforms state-of-the-art GCL methods, underscoring its adaptability and efficacy across various domains.