Generating Counterfactual Hard Negative Samples for Graph Contrastive Learning

by   Haoran Yang, et al.
University of Technology Sydney
The Chinese University of Hong Kong
Curtin University

Graph contrastive learning has emerged as a powerful tool for unsupervised graph representation learning. The key to the success of graph contrastive learning is to acquire high-quality positive and negative samples as contrasting pairs for the purpose of learning underlying structural semantics of the input graph. Recent works usually sample negative samples from the same training batch with the positive samples, or from an external irrelevant graph. However, a significant limitation lies in such strategies, which is the unavoidable problem of sampling false negative samples. In this paper, we propose a novel method to utilize Counterfactual mechanism to generate artificial hard negative samples for Graph Contrastive learning, namely CGC, which has a different perspective compared to those sampling-based strategies. We utilize counterfactual mechanism to produce hard negative samples, which ensures that the generated samples are similar to, but have labels that different from the positive sample. The proposed method achieves satisfying results on several datasets compared to some traditional unsupervised graph learning methods and some SOTA graph contrastive learning methods. We also conduct some supplementary experiments to give an extensive illustration of the proposed method, including the performances of CGC with different hard negative samples and evaluations for hard negative samples generated with different similarity measurements.


page 1

page 3

page 7


Synthetic Hard Negative Samples for Contrastive Learning

Contrastive learning has emerged as an essential approach for self-super...

Dual Space Graph Contrastive Learning

Unsupervised graph representation learning has emerged as a powerful too...

Graph Contrastive Topic Model

Existing NTMs with contrastive learning suffer from the sample bias prob...

SCE: Scalable Network Embedding from Sparsest Cut

Large-scale network embedding is to learn a latent representation for ea...

Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings

Learning scientific document representations can be substantially improv...

SUVR: A Search-based Approach to Unsupervised Visual Representation Learning

Unsupervised learning has grown in popularity because of the difficulty ...

Hard Sample Aware Network for Contrastive Deep Graph Clustering

Contrastive deep graph clustering, which aims to divide nodes into disjo...

Please sign up or login with your details

Forgot password? Click here to reset