GAUSS: GrAph-customized Universal Self-Supervised Learning

Liang Yang, Weixiao Hu, Jizhong Xu, Runjie Shi, Dongxiao He, Chuan Wang, Xiaochun Cao, Zhen Wang, Bingxin Niu, Yuanfang Guo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

To make Graph Neural Networks (GNNs) meet the requirements of the Web, the universality and the generalization become two important research directions. On one hand, many universal GNNs are presented for semi-supervised tasks on both homophilic and non-homophilic graphs by distinguishing homophilic and heterophilic edges with the help of labels. On the other hand, self-supervised learning (SSL) algorithms on graphs are presented by leveraging the self-supervised learning schemes from computer vision and natural language processing. Unfortunately, graph universal self-supervised learning remains resolved. Most existing SSL methods on graphs, which often employ two-layer GCN as the encoder and train the mapping functions, can't alter the low-passing filtering characteristic of GCN. Therefore, to be universal, SSL must becustomized for the graph, i.e., learning the graph. However, learning the graph via universal GNNs is disabled in SSL, since their distinguishability on homophilic and heterophilic edges disappears without the labels. To overcome this difficulty, this paper proposes novel GrAph-customized Universal Self-Supervised Learning (GAUSS) by exploiting local attribute distribution. The main idea is to replace the global parameters with locally learnable propagation. To make the propagation matrix demonstrate the affinity between the nodes, the self-representative learning framework is employed with k-block diagonal regularization. Extensive experiments on synthetic and real-world datasets demonstrate its effectiveness, universality and robustness to noises.

Original languageEnglish
Title of host publicationWWW 2024 - Proceedings of the ACM Web Conference
PublisherAssociation for Computing Machinery, Inc
Pages582-593
Number of pages12
ISBN (Electronic)9798400701719
DOIs
StatePublished - 13 May 2024
Event33rd ACM Web Conference, WWW 2024 - Singapore, Singapore
Duration: 13 May 202417 May 2024

Publication series

NameWWW 2024 - Proceedings of the ACM Web Conference

Conference

Conference33rd ACM Web Conference, WWW 2024
Country/TerritorySingapore
CitySingapore
Period13/05/2417/05/24

Keywords

  • graph neural networks
  • self-representative learning
  • self-supervised learning on graphs
  • universal representation learning

Fingerprint

Dive into the research topics of 'GAUSS: GrAph-customized Universal Self-Supervised Learning'. Together they form a unique fingerprint.

Cite this