Feature-Contrastive Graph Federated Learning: Responsible AI in Graph Information Analysis

doi:10.1109/TCSS.2022.3230987

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	Feature-Contrastive Graph Federated Learning: Responsible AI in Graph Information Analysis
	Zeng, Xingjie 1; Zhou, Tao 1; Bao, Zhicheng 1; Zhao, Hongwei 1; Chen, Leiming 1; Wang, Xiao2,3,4 ; Wang, Feiyue5
发表期刊	IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
ISSN	2329-924X
	2022-12-29
页码	11
通讯作者	Zeng, Xingjie(zengxjupc@163.com)
摘要	Federated learning enables multiple clients to learn a general model without sharing local data, and the federated learning system also improves information security and advances responsible artificial intelligence (AI). However, the data of different clients in the system are non-independently and identically distributed (IID), which results in weight divergence, especially for complex graph data extraction. This article proposes a novel feature-contrastive graph federated (FcgFed) learning approach to improve the robustness of the federated learning system in graph data. First, we design an architecture for FcgFed learning systems to analyze graph information. Furthermore, we present a graph federated learning method based on contrastive learning to alleviate the weight divergence in federated learning. The experiments in node classification and graph classification demonstrate that our method achieves better performance than model-contrastive federated learning (MOON) and federated average (FedAvg). We also test the adaptability of our method in image classification, and the results demonstrate that weight similarity evaluation works for other frameworks and tasks.
关键词	Federated learning Data models Artificial intelligence Graph neural networks Training Learning systems Servers graph neural networks responsible artificial intelligence (AI) weight divergence weight similarity evaluation
DOI	10.1109/TCSS.2022.3230987
关键词[WOS]	NEURAL-NETWORKS
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62072469]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Cybernetics ; Computer Science, Information Systems
WOS记录号	WOS:000910550800001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/51064
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Zeng, Xingjie
作者单位	1.China Univ Petr East China, Dept Coll Comp Sci & Technol, Qingdao 266580, Peoples R China 2.Anhui Univ, Sch Artificial Intelligence e, Hefei 266114, Peoples R China 3.Qingdao Acad Intelligent Ind, Qingdao 230031, Peoples R China 4.Chinese Acad Sci, Inst Automation, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zeng, Xingjie,Zhou, Tao,Bao, Zhicheng,et al. Feature-Contrastive Graph Federated Learning: Responsible AI in Graph Information Analysis[J]. IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,2022:11.
APA	Zeng, Xingjie.,Zhou, Tao.,Bao, Zhicheng.,Zhao, Hongwei.,Chen, Leiming.,...&Wang, Feiyue.(2022).Feature-Contrastive Graph Federated Learning: Responsible AI in Graph Information Analysis.IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,11.
MLA	Zeng, Xingjie,et al."Feature-Contrastive Graph Federated Learning: Responsible AI in Graph Information Analysis".IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS (2022):11.