Paper Info
Title
Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification.
Abstract
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 underexplored. 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.
Year
DOI
Venue
2022
10.24963/ijcai.2022/395
European Conference on Artificial Intelligence
Keywords
DocType
Citations 
Machine Learning: Sequence and Graph Learning,Data Mining: Mining Graphs,Machine Learning: Semi-Supervised Learning
Conference
0
PageRank 
References 
Authors
0.34
0
7
Name
Order
Citations
PageRank
Deli Chen172.81
Yankai Lin260728.37
Li, Lei379969.54
Xuancheng Ren43612.38
Peng Li514621.34
Jie Zhou62103190.17
Xu Sun756468.04