Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning

2021/04/13 by Chen, Shiyi, Wang, Ziao, Zhang, Xinni +2
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2104.06317

Abstract

Graph representation learning has long been an important yet challenging task for various real-world applications. However, their downstream tasks are mainly performed in the settings of supervised or semi-supervised learning. Inspired by recent advances in unsupervised contrastive learning, this paper is thus motivated to investigate how the node-wise contrastive learning could be performed. Particularly, we respectively resolve the class collision issue and the imbalanced negative data distribution issue. Extensive experiments are performed on three real-world datasets and the proposed approach achieves the SOTA model performance.

Related

• Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling
• From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning
• Contrastive Learning with Negative Sampling Correction
• Understanding Negative Sampling in Graph Representation Learning
• Prototypical Graph Contrastive Learning