Towards robust graph neural networks for noisy graphs with sparse labels

Enyan Dai, Wei Jin, Hui Liu, Suhang Wang

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

42 Scopus citations

Abstract

Graph Neural Networks (GNNs) have shown their great ability in modeling graph structured data. However, real-world graphs usually contain structure noises and have limited labeled nodes. The performance of GNNs would drop significantly when trained on such graphs, which hinders the adoption of GNNs on many applications. Thus, it is important to develop noise-resistant GNNs with limited labeled nodes. However, the work on this is rather limited. Therefore, we study a novel problem of developing robust GNNs on noisy graphs with limited labeled nodes. Our analysis shows that both the noisy edges and limited labeled nodes could harm the message-passing mechanism of GNNs. To mitigate these issues, we propose a novel framework which adopts the noisy edges as supervision to learn a denoised and dense graph, which can down-weight or eliminate noisy edges and facilitate message passing of GNNs to alleviate the issue of limited labeled nodes. The generated edges are further used to regularize the predictions of unlabeled nodes with label smoothness to better train GNNs. Experimental results on real-world datasets demonstrate the robustness of the proposed framework on noisy graphs with limited labeled nodes.

Original languageEnglish (US)
Title of host publicationWSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining
PublisherAssociation for Computing Machinery, Inc
Pages181-191
Number of pages11
ISBN (Electronic)9781450391320
DOIs
StatePublished - Feb 11 2022
Event15th ACM International Conference on Web Search and Data Mining, WSDM 2022 - Virtual, Online, United States
Duration: Feb 21 2022Feb 25 2022

Publication series

NameWSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining

Conference

Conference15th ACM International Conference on Web Search and Data Mining, WSDM 2022
Country/TerritoryUnited States
CityVirtual, Online
Period2/21/222/25/22

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'Towards robust graph neural networks for noisy graphs with sparse labels'. Together they form a unique fingerprint.

Cite this