A Unified View on Graph Neural Networks as Graph Signal Denoising

Yao Ma, Xiaorui Liu, Tong Zhao, Yozen Liu, Jiliang Tang, Neil Shah

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

56 Scopus citations

Abstract

Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data. A single GNN layer typically consists of a feature transformation and a feature aggregation operation. The former normally uses feed-forward networks to transform features, while the latter aggregates the transformed features over the graph. Numerous recent works have proposed GNN models with different designs in the aggregation operation. In this work, we establish mathematically that the aggregation processes in a group of representative GNN models including GCN, GAT, PPNP, and APPNP can be regarded as (approximately) solving a graph denoising problem with a smoothness assumption. Such a unified view across GNNs not only provides a new perspective to understand a variety of aggregation operations but also enables us to develop a unified graph neural network framework UGNN. To demonstrate its promising potential, we instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes. Comprehensive experiments show the effectiveness of ADA-UGNN.

Original languageEnglish (US)
Title of host publicationCIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages1202-1211
Number of pages10
ISBN (Electronic)9781450384469
DOIs
StatePublished - Oct 26 2021
Event30th ACM International Conference on Information and Knowledge Management, CIKM 2021 - Virtual, Online, Australia
Duration: Nov 1 2021Nov 5 2021

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Conference

Conference30th ACM International Conference on Information and Knowledge Management, CIKM 2021
Country/TerritoryAustralia
CityVirtual, Online
Period11/1/2111/5/21

All Science Journal Classification (ASJC) codes

  • General Business, Management and Accounting
  • General Decision Sciences

Keywords

  • graph neural networks
  • graph signal denoising
  • semi-supervised classification

Fingerprint

Dive into the research topics of 'A Unified View on Graph Neural Networks as Graph Signal Denoising'. Together they form a unique fingerprint.

Cite this