Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning
This work improves graph representation learning for downstream tasks, but it is incremental as it builds on existing contrastive learning methods.
The paper tackled the problem of learning graph representations via unsupervised contrastive learning by addressing class collision and imbalanced negative data distribution issues, achieving state-of-the-art performance on three real-world datasets.
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.