Subgraph Adaptive Structure-Aware Graph Contrastive Learning
-
Published:2022-08-24
Issue:17
Volume:10
Page:3047
-
ISSN:2227-7390
-
Container-title:Mathematics
-
language:en
-
Short-container-title:Mathematics
Author:
Chen Zhikui,Peng Yin,Yu Shuo,Cao Chen,Xia Feng
Abstract
Graph contrastive learning (GCL) has been subject to more attention and been widely applied to numerous graph learning tasks such as node classification and link prediction. Although it has achieved great success and even performed better than supervised methods in some tasks, most of them depend on node-level comparison, while ignoring the rich semantic information contained in graph topology, especially for social networks. However, a higher-level comparison requires subgraph construction and encoding, which remain unsolved. To address this problem, we propose a subgraph adaptive structure-aware graph contrastive learning method (PASCAL) in this work, which is a subgraph-level GCL method. In PASCAL, we construct subgraphs by merging all motifs that contain the target node. Then we encode them on the basis of motif number distribution to capture the rich information hidden in subgraphs. By incorporating motif information, PASCAL can capture richer semantic information hidden in local structures compared with other GCL methods. Extensive experiments on six benchmark datasets show that PASCAL outperforms state-of-art graph contrastive learning and supervised methods in most cases.
Funder
National Key Research and Development Program of China
National Natural Science Foundation of China
Fundamental Research Funds for the Central Universities
Subject
General Mathematics,Engineering (miscellaneous),Computer Science (miscellaneous)
Reference45 articles.
1. A Triple-Step Asynchronous Federated Learning Mechanism for Client Activation, Interaction Optimization, and Aggregation Enhancement
2. A new link prediction in multiplex networks using topologically biased random walks
3. Graph Learning: A Survey
4. Graph Attention Networks;Veličković;Proceedings of the International Conference on Learning Representations,2018
5. Inductive Representation Learning on Large Graphs;Hamilton;Proceedings of the 31st International Conference on Neural Information Processing Systems,2017