Dual Space Graph Contrastive Learning

Haoran Yang, Hongxu Chen, Shirui Pan, Lin Li, Philip S. Yu, Guandong Xu

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

3 Citations (Scopus)

Abstract

Unsupervised graph representation learning has emerged as a powerful tool to address real-world problems and achieves huge success in the graph learning domain. Graph contrastive learning is one of the unsupervised graph representation learning methods, which recently attracts attention from researchers and has achieved state-of-the-art performances on various tasks. The key to the success of graph contrastive learning is to construct proper contrasting pairs to acquire the underlying structural semantics of the graph. However, this key part is not fully explored currently, most of the ways generating contrasting pairs focus on augmenting or perturbating graph structures to obtain different views of the input graph. But such strategies could degrade the performances via adding noise into the graph, which may narrow down the field of the applications of graph contrastive learning. In this paper, we propose a novel graph contrastive learning method, namely Dual Space Graph Contrastive (DSGC) Learning, to conduct graph contrastive learning among views generated in different spaces including the hyperbolic space and the Euclidean space. Since both spaces have their own advantages to represent graph data in the embedding spaces, we hope to utilize graph contrastive learning to bridge the spaces and leverage advantages from both sides. The comparison experiment results show that DSGC achieves competitive or better performances among all the datasets. In addition, we conduct extensive experiments to analyze the impact of different graph encoders on DSGC, giving insights about how to better leverage the advantages of contrastive learning between different spaces.

Original languageEnglish
Title of host publicationWWW'22 - Proceedings of the ACM Web Conference 2022
EditorsIvan Herman, Lionel Medini
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Pages1238-1247
Number of pages10
ISBN (Electronic)9781450390965
DOIs
Publication statusPublished - 2022
EventInternational World Wide Web Conference 2022 - Virtual, Online, France
Duration: 25 Apr 202229 Apr 2022
Conference number: 31st
https://www2022.thewebconf.org/

Conference

ConferenceInternational World Wide Web Conference 2022
Abbreviated titleWWW 2022
Country/TerritoryFrance
CityVirtual, Online
Period25/04/2229/04/22
Internet address

Keywords

  • graph contrastive learning
  • graph embedding
  • hyperbolic space

Cite this