Learning to Drop: Robust Graph Neural Network via Topological Denoising

Dongsheng Luo, Wei Cheng, Wenchao Yu, Bo Zong, Jingchao Ni, Haifeng Chen, Xiang Zhang

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

1 Scopus citations

Abstract

Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is to recursively propagate and aggregate information along the edges of the given graph. Despite their success, however, the existing GNNs are usually sensitive to the quality of the input graph. Real-world graphs are often noisy and contain task-irrelevant edges, which may lead to suboptimal generalization performance in the learned GNN models. In this paper, we propose PTDNet, a parameterized topological denoising network, to improve the robustness and generalization performance of GNNs by learning to drop task-irrelevant edges. PTDNet prunes task-irrelevant edges by penalizing the number of edges in the sparsified graph with parameterized networks. To take into consideration the topology of the entire graph, the nuclear norm regularization is applied to impose the low-rank constraint on the resulting sparsified graph for better generalization. PTDNet can be used as a key component in GNN models to improve their performances on various tasks, such as node classification and link prediction. Experimental studies on both synthetic and benchmark datasets show that PTDNet can improve the performance of GNNs significantly and the performance gain becomes larger for more noisy datasets.

Original languageEnglish (US)
Title of host publicationWSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining
PublisherAssociation for Computing Machinery, Inc
Pages779-787
Number of pages9
ISBN (Electronic)9781450382977
DOIs
StatePublished - Aug 3 2021
Event14th ACM International Conference on Web Search and Data Mining, WSDM 2021 - Virtual, Online, Israel
Duration: Mar 8 2021Mar 12 2021

Publication series

NameWSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining

Conference

Conference14th ACM International Conference on Web Search and Data Mining, WSDM 2021
Country/TerritoryIsrael
CityVirtual, Online
Period3/8/213/12/21

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'Learning to Drop: Robust Graph Neural Network via Topological Denoising'. Together they form a unique fingerprint.

Cite this