File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Semi-supervised domain adaptation on graphs with contrastive learning and minimax entropy

TitleSemi-supervised domain adaptation on graphs with contrastive learning and minimax entropy
Authors
KeywordsAdversarial learning
Graph contrastive learning
Graph transfer learning
Node classification
Semi-supervised domain adaptation
Issue Date1-May-2024
PublisherElsevier
Citation
Neurocomputing, 2024, v. 580 How to Cite?
AbstractLabel scarcity in a graph is frequently encountered in real-world applications due to the high cost of data labeling. To this end, semi-supervised domain adaptation (SSDA) on graphs aims to leverage the knowledge of a labeled source graph to aid in node classification on a target graph with limited labels. SSDA tasks need to overcome the domain gap between the source and target graphs. However, to date, this challenging research problem has yet to be formally considered by the existing approaches designed for cross-graph node classification. This paper proposes a novel method called SemiGCL to tackle the graph Semi-supervised domain adaptation with Graph Contrastive Learning and minimax entropy training. SemiGCL generates informative node representations by contrasting the representations learned from a graph's local and global views. Additionally, SemiGCL is adversarially optimized with the entropy loss of unlabeled target nodes to reduce domain divergence. Experimental results on benchmark datasets demonstrate that SemiGCL outperforms the state-of-the-art baselines on the SSDA tasks.
Persistent Identifierhttp://hdl.handle.net/10722/344367
ISSN
2023 Impact Factor: 5.5
2023 SCImago Journal Rankings: 1.815

 

DC FieldValueLanguage
dc.contributor.authorXiao, Jiaren-
dc.contributor.authorDai, Quanyu-
dc.contributor.authorShen, Xiao-
dc.contributor.authorXie, Xiaochen-
dc.contributor.authorDai, Jing-
dc.contributor.authorLam, James-
dc.contributor.authorKwok, Ka Wai-
dc.date.accessioned2024-07-24T13:51:02Z-
dc.date.available2024-07-24T13:51:02Z-
dc.date.issued2024-05-01-
dc.identifier.citationNeurocomputing, 2024, v. 580-
dc.identifier.issn0925-2312-
dc.identifier.urihttp://hdl.handle.net/10722/344367-
dc.description.abstractLabel scarcity in a graph is frequently encountered in real-world applications due to the high cost of data labeling. To this end, semi-supervised domain adaptation (SSDA) on graphs aims to leverage the knowledge of a labeled source graph to aid in node classification on a target graph with limited labels. SSDA tasks need to overcome the domain gap between the source and target graphs. However, to date, this challenging research problem has yet to be formally considered by the existing approaches designed for cross-graph node classification. This paper proposes a novel method called SemiGCL to tackle the graph Semi-supervised domain adaptation with Graph Contrastive Learning and minimax entropy training. SemiGCL generates informative node representations by contrasting the representations learned from a graph's local and global views. Additionally, SemiGCL is adversarially optimized with the entropy loss of unlabeled target nodes to reduce domain divergence. Experimental results on benchmark datasets demonstrate that SemiGCL outperforms the state-of-the-art baselines on the SSDA tasks.-
dc.languageeng-
dc.publisherElsevier-
dc.relation.ispartofNeurocomputing-
dc.subjectAdversarial learning-
dc.subjectGraph contrastive learning-
dc.subjectGraph transfer learning-
dc.subjectNode classification-
dc.subjectSemi-supervised domain adaptation-
dc.titleSemi-supervised domain adaptation on graphs with contrastive learning and minimax entropy-
dc.typeArticle-
dc.identifier.doi10.1016/j.neucom.2024.127469-
dc.identifier.scopuseid_2-s2.0-85187173299-
dc.identifier.volume580-
dc.identifier.eissn1872-8286-
dc.identifier.issnl0925-2312-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats