Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning

Abstract

Graph contrastive learning (GCL), standing as the dominant paradigm in the realm of graph pre-training, has yielded considerable progress. Nonetheless, its capacity for out-of-distribution (OOD) generalization has been relatively underexplored. In this work, we point out that the traditional optimization of InfoNCE in GCL restricts the cross-domain pairs only to be negative samples, which inevitably enlarges the distribution gap between different domains. This violates the requirement of domain invariance under OOD scenario and consequently impairs the model's OOD generalization performance. To address this issue, we propose a novel strategy "Negative as Positive", where the most semantically similar cross-domain negative pairs are treated as positive during GCL. Our experimental results, spanning a wide array of datasets, confirm that this method substantially improves the OOD generalization performance of GCL.

arXiv comment5 pages, 5 figures, In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '24), July 14-18, 2024, Washington, DC, USA

References in corpus (7)

• Graph Contrastive Learning with Adaptive Augmentation
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
• COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning
• GOOD: A Graph Out-of-Distribution Benchmark
• Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network
• Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer
• Causality and Independence Enhancement for Biased Node Classification

Cited by in corpus (1)

• InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning