Subgraph Networks Based Contrastive Learning

arXiv:2306.03506v2 Announce Type: replace
Abstract: Graph contrastive learning (GCL), as a self-supervised learning method, can solve the problem of annotated data scarcity. It mines explicit features in unannotated graphs to generate favorable graph representations for downstream tasks. Most existing GCL methods focus on the design of graph augmentation strategies and mutual information estimation operations. Graph augmentation produces augmented views by graph perturbations. These views preserve a locally similar structure and exploit explicit features. However, these methods have not considered the …

abstract annotated data arxiv augmentation cs.ai cs.lg data design features focus generate graph graphs information networks operations self-supervised learning solve strategies supervised learning tasks type