Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification
This work aims to improve semi-supervised node classification for researchers and practitioners working with graph data by proposing a more effective graph contrastive learning framework.
This paper investigates the working mechanism of Graph Contrastive Learning (GCL) in Semi-Supervised Node Classification (SSNC), finding that GCL's benefits are unevenly distributed, primarily aiding subgraphs with less annotated information. To address this, they propose TIFA-GCL, which considers the distribution of annotated information, leading to larger improvements than existing GCL methods on six benchmark datasets, including OGB-Products.
Graph Contrastive Learning (GCL) has proven highly effective in promoting the performance of Semi-Supervised Node Classification (SSNC). However, existing GCL methods are generally transferred from other fields like CV or NLP, whose underlying working mechanism remains under-explored. In this work, we first deeply probe the working mechanism of GCL in SSNC, and find that the promotion brought by GCL is severely unevenly distributed: the improvement mainly comes from subgraphs with less annotated information, which is fundamentally different from contrastive learning in other fields. However, existing GCL methods generally ignore this uneven distribution of annotated information and apply GCL evenly to the whole graph. To remedy this issue and further improve GCL in SSNC, we propose the Topology InFormation gain-Aware Graph Contrastive Learning (TIFA-GCL) framework that considers the annotated information distribution across graph in GCL. Extensive experiments on six benchmark graph datasets, including the enormous OGB-Products graph, show that TIFA-GCL can bring a larger improvement than existing GCL methods in both transductive and inductive settings. Further experiments demonstrate the generalizability and interpretability of TIFA-GCL.