Learning Augmentation for GNNs With Consistency Regularization
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Hyeonjin | - |
dc.contributor.author | Lee, Seunghun | - |
dc.contributor.author | Hwang, Dasol | - |
dc.contributor.author | Jeong, Jisu | - |
dc.contributor.author | Kim, Kyung-Min | - |
dc.contributor.author | Ha, Jung-Woo | - |
dc.contributor.author | Kim, Hyunwoo J. | - |
dc.date.accessioned | 2022-03-12T04:41:03Z | - |
dc.date.available | 2022-03-12T04:41:03Z | - |
dc.date.created | 2022-01-20 | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/138680 | - |
dc.description.abstract | Graph neural networks (GNNs) have demonstrated superior performance in various tasks on graphs. However, existing GNNs often suffer from weak-generalization due to sparsely labeled datasets. Here we propose a novel framework that learns to augment the input features using topological information and automatically controls the strength of augmentation. Our framework learns the augmentor to minimize GNNs' loss on unseen labeled data while maximizing the consistency of GNNs' predictions on unlabeled data. This can be formulated as a meta-learning problem and our framework alternately optimizes the augmentor and GNNs for a target task. Our extensive experiments demonstrate that the proposed framework is applicable to any GNNs and significantly improves the performance of graph neural networks on node classification. In particular, our method provides 5.78% improvement with Graph convolutional network (GCN) on average across five benchmark datasets. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | REPRESENTATION | - |
dc.title | Learning Augmentation for GNNs With Consistency Regularization | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Hyunwoo J. | - |
dc.identifier.doi | 10.1109/ACCESS.2021.3111908 | - |
dc.identifier.scopusid | 2-s2.0-85114713827 | - |
dc.identifier.wosid | 000697808000001 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.9, pp.127961 - 127972 | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 9 | - |
dc.citation.startPage | 127961 | - |
dc.citation.endPage | 127972 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordPlus | REPRESENTATION | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Graph neural networks | - |
dc.subject.keywordAuthor | Topology | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Data models | - |
dc.subject.keywordAuthor | Licenses | - |
dc.subject.keywordAuthor | Training data | - |
dc.subject.keywordAuthor | Graph neural networks | - |
dc.subject.keywordAuthor | augmentation | - |
dc.subject.keywordAuthor | semi-supervised learning | - |
dc.subject.keywordAuthor | meta-learning | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.