Graph Contrastive Learning with Cohesive Subgraph Awareness
arXiv:2401.17580 · doi:10.1145/3589334.3645470
Abstract
Graph contrastive learning (GCL) has emerged as a state-of-the-art strategy for learning representations of diverse graphs including social and biomedical networks. GCL widely uses stochastic graph topology augmentation, such as uniform node dropping, to generate augmented graphs. However, such stochastic augmentations may severely damage the intrinsic properties of a graph and deteriorate the following representation learning process. We argue that incorporating an awareness of cohesive subgraphs during the graph augmentation and learning processes has the potential to enhance GCL performance. To this end, we propose a novel unified framework called CTAug, to seamlessly integrate cohesion awareness into various existing GCL mechanisms. In particular, CTAug comprises two specialized modules: topology augmentation enhancement and graph learning enhancement. The former module generates augmented graphs that carefully preserve cohesion properties, while the latter module bolsters the graph encoder's ability to discern subgraph patterns. Theoretical analysis shows that CTAug can strictly improve existing GCL mechanisms. Empirical experiments verify that CTAug can achieve state-of-the-art performance for graph representation learning, especially for graphs with high degrees. The code is available at https://doi.org/10.5281/zenodo.10594093, or https://github.com/wuyucheng2002/CTAug.
References in corpus (9)
- Identification of influential spreaders in complex networks
- Graph Contrastive Learning with Adaptive Augmentation
- Curvature of Co-Links Uncovers Hidden Thematic Layers in the World Wide Web
- Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
- SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation
- Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
- Adversarial Graph Augmentation to Improve Graph Contrastive Learning
- Resilience and rewiring of the passenger airline networks in the United States
- Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrum