CGCL: Collaborative Graph Contrastive Learning without Handcrafted Graph Data Augmentations

TL;DR

This paper introduces CGCL, a novel unsupervised graph representation learning method that uses multiple encoders to generate contrastive views without relying on handcrafted graph augmentations, improving stability and invariance.

Contribution

The paper proposes a collaborative framework with multiple graph encoders and asymmetric architectures to avoid unstable augmentations in contrastive learning.

Findings

CGCL outperforms existing methods in unsupervised graph-level tasks.

The collaborative approach enhances invariance and stability.

Quantitative metrics validate the effectiveness of the framework.

Abstract

Unsupervised graph representation learning is a non-trivial topic. The success of contrastive methods in the unsupervised representation learning on structured data inspires similar attempts on the graph. Existing graph contrastive learning (GCL) aims to learn the invariance across multiple augmentation views, which renders it heavily reliant on the handcrafted graph augmentations. However, inappropriate graph data augmentations can potentially jeopardize such invariance. In this paper, we show the potential hazards of inappropriate augmentations and then propose a novel Collaborative Graph Contrastive Learning framework (CGCL). This framework harnesses multiple graph encoders to observe the graph. Features observed from different encoders serve as the contrastive views in contrastive learning, which avoids inducing unstable perturbation and guarantees the invariance. To ensure the collaboration among diverse graph encoders, we propose the concepts of asymmetric architecture and complementary encoders as the design principle. To further prove the rationality, we utilize two quantitative metrics to measure the assembly of CGCL respectively. Extensive experiments demonstrate the advantages of CGCL in unsupervised graph-level representation learning and the potential of collaborative framework. The source code for reproducibility is available at https://github.com/zhangtia16/CGCL