Improving Graph Representation Learning with Distribution Preserving

Chengsheng Mao*, Yuan Luo

*Corresponding author for this work

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

Abstract

Graph neural network (GNN) is effective to model graphs for distributed representations of nodes and an entire graph. Recently, research on the expressive power of GNN attracted growing attention. A highly expressive GNN has the ability to generate discriminative graph representations. However, in the end-to-end training process for a certain graph learning task, an expressive GNN could generate graph representations overfitting the training data for the target task but losing information important for the model generalization, thus reducing the generalizability. In this paper, we propose Distribution Preserving GNN (DP-GNN), a GNN framework that can improve the generalizability of expressive GNN models by preserving several kinds of distribution information in graph representations and node representations. Besides the generalizability, by applying an expressive GNN backbone, DP-GNN can also have high expressive power. We evaluate the proposed DP-GNN framework on multiple benchmark datasets for graph classification tasks. The experimental results demonstrate that our model achieves state-of-the-art performances.

Original languageEnglish (US)
Title of host publicationProceedings - 22nd IEEE International Conference on Data Mining, ICDM 2022
EditorsXingquan Zhu, Sanjay Ranka, My T. Thai, Takashi Washio, Xindong Wu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1095-1100
Number of pages6
ISBN (Electronic)9781665450997
DOIs
StatePublished - 2022
Event22nd IEEE International Conference on Data Mining, ICDM 2022 - Orlando, United States
Duration: Nov 28 2022Dec 1 2022

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
Volume2022-November
ISSN (Print)1550-4786

Conference

Conference22nd IEEE International Conference on Data Mining, ICDM 2022
Country/TerritoryUnited States
CityOrlando
Period11/28/2212/1/22

Funding

The research is supported in part by the following US NIH grants: R21LM012618, 5UL1TR001422, U01TR003528 and R01LM013337.

Keywords

  • expressive power
  • generalizability
  • Graph neural network
  • graph representation
  • multi-task learning

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Improving Graph Representation Learning with Distribution Preserving'. Together they form a unique fingerprint.

Cite this