Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning

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.

References in corpus (6)

• Inductive Representation Learning on Large Graphs
• struc2vec: Learning Node Representations from Structural Identity
• Variational Graph Auto-Encoders
• Predicting multicellular function through multi-layer tissue networks
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs