SUGAR: subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism

Qingyun Sun, Jianxin Li, Hao Peng, Jia Wu, Yuanxing Ning, Phillip S. Yu, Lifang He

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

26 Downloads (Pure)

Abstract

Graph representation learning has attracted increasing research attention. However, most existing studies fuse all structural features and node attributes to provide an overarching view of graphs, neglecting finer substructures' semantics, and suffering from interpretation enigmas. This paper presents a novel hierarchical subgraph-level selection and embedding-based graph neural network for graph classification, namely SUGAR, to learn more discriminative subgraph representations and respond in an explanatory way. SUGAR reconstructs a sketched graph by extracting striking subgraphs as the representative part of the original graph to reveal subgraph-level patterns. To adaptively select striking subgraphs without prior knowledge, we develop a reinforcement pooling mechanism, which improves the generalization ability of the model. To differentiate subgraph representations among graphs, we present a self-supervised mutual information mechanism to encourage subgraph embedding to be mindful of the global graph structural properties by maximizing their mutual information. Extensive experiments on six typical bioinformatics datasets demonstrate a significant and consistent improvement in model quality with competitive performance and interpretability.

Original languageEnglish
Title of host publicationThe Web Conference 2021
Subtitle of host publicationProceedings of the World Wide Web Conference, WWW 2021
Place of PublicationNew York, NY
PublisherAssociation for Computing Machinery, Inc
Pages2081-2091
Number of pages11
ISBN (Electronic)9781450383127
DOIs
Publication statusPublished - 2021
Event2021 World Wide Web Conference, WWW 2021 - Ljubljana, Slovenia
Duration: 19 Apr 202123 Apr 2021

Publication series

NameThe Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021

Conference

Conference2021 World Wide Web Conference, WWW 2021
CountrySlovenia
CityLjubljana
Period19/04/2123/04/21

Bibliographical note

Copyright the Publisher 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

  • Graph Classification
  • Graph Neural Networks
  • Graph Pooling
  • Mutual Information
  • Reinforcement Learning

Fingerprint

Dive into the research topics of 'SUGAR: subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism'. Together they form a unique fingerprint.

Cite this