用于节点和图分类的独特异构增强图对比学习框架

IF 6.7 2区 计算机科学 Q1 ENGINEERING, MULTIDISCIPLINARY IEEE Transactions on Network Science and Engineering Pub Date : 2024-09-09 DOI:10.1109/TNSE.2024.3454993
Qi Shao;Duxin Chen;Wenwu Yu
{"title":"用于节点和图分类的独特异构增强图对比学习框架","authors":"Qi Shao;Duxin Chen;Wenwu Yu","doi":"10.1109/TNSE.2024.3454993","DOIUrl":null,"url":null,"abstract":"Graph contrastive learning has gained significant attention for its effectiveness in leveraging unlabeled data and achieving superior performance. However, prevalent graph contrastive learning methods often resort to graph augmentation, typically involving the removal of anchor graph structures. This strategy may compromise the essential graph information, constraining the adaptability of contrastive learning approaches across diverse tasks. To overcome this limitation, we introduce a novel augmentation technique for graph contrastive learning: \n<italic>heterogeneous augmentation</i>\n. Through the application of heterogeneous augmentation to homogeneous anchor graphs, our method obviates the need for modifying edges and nodes, preserving the structural integrity of the anchor graph to the fullest extent. The proposed method could become a significant technique in graph augmentation, potentially influencing further research and development in this area. Our work provides a valuable contribution to the advancement of graph contrastive learning methodologies.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"5818-5828"},"PeriodicalIF":6.7000,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Unique Framework of Heterogeneous Augmentation Graph Contrastive Learning for Both Node and Graph Classification\",\"authors\":\"Qi Shao;Duxin Chen;Wenwu Yu\",\"doi\":\"10.1109/TNSE.2024.3454993\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Graph contrastive learning has gained significant attention for its effectiveness in leveraging unlabeled data and achieving superior performance. However, prevalent graph contrastive learning methods often resort to graph augmentation, typically involving the removal of anchor graph structures. This strategy may compromise the essential graph information, constraining the adaptability of contrastive learning approaches across diverse tasks. To overcome this limitation, we introduce a novel augmentation technique for graph contrastive learning: \\n<italic>heterogeneous augmentation</i>\\n. Through the application of heterogeneous augmentation to homogeneous anchor graphs, our method obviates the need for modifying edges and nodes, preserving the structural integrity of the anchor graph to the fullest extent. The proposed method could become a significant technique in graph augmentation, potentially influencing further research and development in this area. Our work provides a valuable contribution to the advancement of graph contrastive learning methodologies.\",\"PeriodicalId\":54229,\"journal\":{\"name\":\"IEEE Transactions on Network Science and Engineering\",\"volume\":\"11 6\",\"pages\":\"5818-5828\"},\"PeriodicalIF\":6.7000,\"publicationDate\":\"2024-09-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Network Science and Engineering\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10670065/\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Network Science and Engineering","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10670065/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

图对比学习能有效利用无标记数据,并取得优异的性能,因此备受关注。然而,目前流行的图对比学习方法通常采用图增强方法,通常涉及移除锚图结构。这种策略可能会损害基本的图信息,限制对比学习方法在不同任务中的适应性。为了克服这一局限,我们为图对比学习引入了一种新的增强技术:异构增强。通过将异构增强应用于同构锚图,我们的方法无需修改边和节点,最大程度地保留了锚图的结构完整性。所提出的方法可能成为图增强领域的一项重要技术,并有可能影响该领域的进一步研究和发展。我们的工作为推动图对比学习方法的发展做出了宝贵贡献。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A Unique Framework of Heterogeneous Augmentation Graph Contrastive Learning for Both Node and Graph Classification
Graph contrastive learning has gained significant attention for its effectiveness in leveraging unlabeled data and achieving superior performance. However, prevalent graph contrastive learning methods often resort to graph augmentation, typically involving the removal of anchor graph structures. This strategy may compromise the essential graph information, constraining the adaptability of contrastive learning approaches across diverse tasks. To overcome this limitation, we introduce a novel augmentation technique for graph contrastive learning: heterogeneous augmentation . Through the application of heterogeneous augmentation to homogeneous anchor graphs, our method obviates the need for modifying edges and nodes, preserving the structural integrity of the anchor graph to the fullest extent. The proposed method could become a significant technique in graph augmentation, potentially influencing further research and development in this area. Our work provides a valuable contribution to the advancement of graph contrastive learning methodologies.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IEEE Transactions on Network Science and Engineering
IEEE Transactions on Network Science and Engineering Engineering-Control and Systems Engineering
CiteScore
12.60
自引率
9.10%
发文量
393
期刊介绍: The proposed journal, called the IEEE Transactions on Network Science and Engineering (TNSE), is committed to timely publishing of peer-reviewed technical articles that deal with the theory and applications of network science and the interconnections among the elements in a system that form a network. In particular, the IEEE Transactions on Network Science and Engineering publishes articles on understanding, prediction, and control of structures and behaviors of networks at the fundamental level. The types of networks covered include physical or engineered networks, information networks, biological networks, semantic networks, economic networks, social networks, and ecological networks. Aimed at discovering common principles that govern network structures, network functionalities and behaviors of networks, the journal seeks articles on understanding, prediction, and control of structures and behaviors of networks. Another trans-disciplinary focus of the IEEE Transactions on Network Science and Engineering is the interactions between and co-evolution of different genres of networks.
期刊最新文献
Table of Contents Guest Editorial: Introduction to the Special Section on Aerial Computing Networks in 6G Guest Editorial: Introduction to the Special Section on Research on Power Technology, Economy and Policy Towards Net-Zero Emissions Temporal Link Prediction via Auxiliary Graph Transformer ULBRF: A Framework for Maximizing Influence in Dynamic Networks Based on Upper and Lower Bounds of Propagation
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1