Graph pooling with representativeness

Juanhui Li, Yao Ma, Yiqi Wang, Charu Aggarwal, Chang Dong Wang, Jiliang Tang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations

Abstract

Graph Neural Networks (GNNs), which extend deep neural networks to graph-structured data, have attracted increasing attention. They have been proven to be powerful for numerous graph related tasks such as graph classification, link prediction, and node classification. To adapt GNNs to graph classification, recent works aim to learn graph-level representation through a hierarchical pooling procedure. One major direction is to select important nodes to hierarchically coarsen the input graph and gradually reduce the information into the graph representation. However, most of the existing methods only select important nodes, which can be redundant and cannot represent the original graph well. Meanwhile, the information of non-selected nodes is often overlooked when generating a new coarser graph, which may lead to the tremendous loss of important structural and node feature information. In this paper, we propose a novel pooling operator RepPool to learn hierarchical graph representations. Specifically, we introduce the concept of representativeness that is combined with the importance for node selection and we provide a learnable way to integrate non-selected nodes. By combining the RepPool operator with conventional GCN convolutional layers, a hierarchical graph classification architecture is developed. Extensive experiments on various public benchmarks have demonstrated the effectiveness of the proposed method. The implementation of the proposed framework is available11https://github.com/Juanhui28/RepPool/tree/master/RepPool.

Original languageEnglish (US)
Title of host publicationProceedings - 20th IEEE International Conference on Data Mining, ICDM 2020
EditorsClaudia Plant, Haixun Wang, Alfredo Cuzzocrea, Carlo Zaniolo, Xindong Wu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages302-311
Number of pages10
ISBN (Electronic)9781728183169
DOIs
StatePublished - Nov 2020
Externally publishedYes
Event20th IEEE International Conference on Data Mining, ICDM 2020 - Virtual, Sorrento, Italy
Duration: Nov 17 2020Nov 20 2020

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
Volume2020-November
ISSN (Print)1550-4786

Conference

Conference20th IEEE International Conference on Data Mining, ICDM 2020
Country/TerritoryItaly
CityVirtual, Sorrento
Period11/17/2011/20/20

All Science Journal Classification (ASJC) codes

  • General Engineering

Keywords

  • Graph neural networks
  • Graph pooling
  • Hierarchical graph representation learning
  • Node importance
  • Node representativeness

Fingerprint

Dive into the research topics of 'Graph pooling with representativeness'. Together they form a unique fingerprint.

Cite this