Hypernetwork-driven centralized contrastive learning for federated graph classification

Jianian Zhu, Yichen Li, Haozhao Wang, Yining Qi, Ruixuan Li
{"title":"Hypernetwork-driven centralized contrastive learning for federated graph classification","authors":"Jianian Zhu, Yichen Li, Haozhao Wang, Yining Qi, Ruixuan Li","doi":"10.1007/s11280-024-01292-1","DOIUrl":null,"url":null,"abstract":"<p>In the domain of Graph Federated Learning (GFL), prevalent methods often focus on local client data, which can limit the understanding of broader global patterns and pose challenges with Non-IID (Non-Independent and Identically Distributed) issues in cross-domain datasets. Direct aggregation can lead to a reduction in the differences among various clients, which is detrimental to personalized datasets. Contrastive Learning (CL) has emerged as an effective tool for enhancing a model’s ability to distinguish variations across diverse views but has not been fully leveraged in GFL. This study introduces a novel hypernetwork-based method, termed CCL (Centralized Contrastive Learning), which is a server-centric innovation that effectively addresses the challenges posed by traditional client-centric approaches in heterogeneous datasets. CCL integrates global patterns from multiple clients, capturing a wider range of patterns and significantly improving GFL performance. Our extensive experiments, including both supervised and unsupervised scenarios, demonstrate CCL’s superiority over existing models, its remarkable compatibility with standard backbones, and its ability to enhance GFL performance across various settings.</p>","PeriodicalId":501180,"journal":{"name":"World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"World Wide Web","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s11280-024-01292-1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

In the domain of Graph Federated Learning (GFL), prevalent methods often focus on local client data, which can limit the understanding of broader global patterns and pose challenges with Non-IID (Non-Independent and Identically Distributed) issues in cross-domain datasets. Direct aggregation can lead to a reduction in the differences among various clients, which is detrimental to personalized datasets. Contrastive Learning (CL) has emerged as an effective tool for enhancing a model’s ability to distinguish variations across diverse views but has not been fully leveraged in GFL. This study introduces a novel hypernetwork-based method, termed CCL (Centralized Contrastive Learning), which is a server-centric innovation that effectively addresses the challenges posed by traditional client-centric approaches in heterogeneous datasets. CCL integrates global patterns from multiple clients, capturing a wider range of patterns and significantly improving GFL performance. Our extensive experiments, including both supervised and unsupervised scenarios, demonstrate CCL’s superiority over existing models, its remarkable compatibility with standard backbones, and its ability to enhance GFL performance across various settings.

Abstract Image

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
针对联合图分类的超网络驱动集中式对比学习
在图形联合学习(GFL)领域,流行的方法通常侧重于本地客户端数据,这可能会限制对更广泛的全局模式的理解,并对跨域数据集中的非独立和相同分布(Non-IID)问题构成挑战。直接聚合会导致减少不同客户之间的差异,这对个性化数据集不利。对比学习(Contrastive Learning,CL)已成为增强模型区分不同视图间差异能力的有效工具,但在 GFL 中尚未得到充分利用。本研究介绍了一种基于超网络的新方法,称为 CCL(集中对比学习),它是一种以服务器为中心的创新方法,能有效解决异构数据集中传统的以客户端为中心的方法所带来的挑战。CCL 整合了来自多个客户端的全局模式,可以捕捉到更广泛的模式,并显著提高 GFL 的性能。我们进行了大量实验,包括有监督和无监督场景,证明了 CCL 优于现有模型、与标准骨干网的显著兼容性以及在各种环境下提高 GFL 性能的能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
HetFS: a method for fast similarity search with ad-hoc meta-paths on heterogeneous information networks A SHAP-based controversy analysis through communities on Twitter pFind: Privacy-preserving lost object finding in vehicular crowdsensing Use of prompt-based learning for code-mixed and code-switched text classification Drug traceability system based on semantic blockchain and on a reputation method
×
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