Dual Space Graph Contrastive Learning

Abstract

Unsupervised graph representation learning has emerged as a powerful tool to address real-world problems and achieves huge success in the graph learning domain. Graph contrastive learning is one of the unsupervised graph representation learning methods, which recently attracts attention from researchers and has achieved state-of-the-art performances on various tasks. The key to the success of graph contrastive learning is to construct proper contrasting pairs to acquire the underlying structural semantics of the graph. However, this key part is not fully explored currently, most of the ways generating contrasting pairs focus on augmenting or perturbating graph structures to obtain different views of the input graph. But such strategies could degrade the performances via adding noise into the graph, which may narrow down the field of the applications of graph contrastive learning. In this paper, we propose a novel graph contrastive learning method, namely \textbf{D}ual \textbf{S}pace \textbf{G}raph \textbf{C}ontrastive (DSGC) Learning, to conduct graph contrastive learning among views generated in different spaces including the hyperbolic space and the Euclidean space. Since both spaces have their own advantages to represent graph data in the embedding spaces, we hope to utilize graph contrastive learning to bridge the spaces and leverage advantages from both sides. The comparison experiment results show that DSGC achieves competitive or better performances among all the datasets. In addition, we conduct extensive experiments to analyze the impact of different graph encoders on DSGC, giving insights about how to better leverage the advantages of contrastive learning between different spaces.

References in corpus (13)

• Learning deep representations by mutual information estimation and maximization
• Proceedings of the 29th International Conference on Machine Learning (ICML-12)
• Graph Convolutional Matrix Completion
• Graph Contrastive Learning with Adaptive Augmentation
• Graph Contrastive Learning with Augmentations
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
• Contrastive Multi-View Representation Learning on Graphs
• Hyperbolic Graph Convolutional Neural Networks
• Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
• Subgraph Matching Kernels for Attributed Graphs
• Hyperbolic Node Embedding for Signed Networks
• HCGR: Hyperbolic Contrastive Graph Representation Learning for Session-based Recommendation
• Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph

Cited by in corpus (6)

• A Comprehensive Survey on Deep Graph Representation Learning
• Generating Counterfactual Hard Negative Samples for Graph Contrastive Learning
• A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning
• Heterogeneous Social Event Detection via Hyperbolic Graph Representations
• A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
• Self-supervised Representation Learning on Electronic Health Records with Graph Kernel Infomax