CLC: A Consensus-based Label Correction Approach in Federated Learning

doi:10.1145/3519311

	CLC: A Consensus-based Label Correction Approach in Federated Learning
	Zeng, Bixiao 1,2,3; Yang, Xiaodong 1,4; Chen, Yiqiang 1,2,3,5; Yu, Hanchao 6; Zhang, Yingwei 1
	2022-10-01
发表期刊	ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
ISSN	2157-6904
卷号	13 期号:5 页码:23
摘要	Federated learning (FL) is a novel distributed learning framework where multiple participants collaboratively train a global model without sharing any raw data to preserve privacy. However, data quality may vary among the participants, the most typical of which is label noise. The incorrect label would significantly damage the performance of the global model. In FL, the inaccessibility of raw data makes this issue more challenging. Previously published studies are limited to using a task-specific benchmark-trained model to evaluate the relevance between the benchmark dataset in the server and the local one on the participants' side. However, such approaches have failed to exploit the cooperative nature of FL itself and are not practical. This paper proposes a Consensus-based Label Correction approach (CLC) in FL, which tries to correct the noisy labels using the developed consensus method among the FL participants. The consensus-defined class-wise information is used to identify the noisy labels and correct them with pseudo-labels. Extensive experiments are conducted on several public datasets in various settings. The experimental results prove the advantage over the state-of-art methods.
关键词	Federated learning data evaluation consensus mechanism
DOI	10.1145/3519311
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Plan of China[2020YFC2007104] ; National Natural Science Foundation of China[61972383] ; Science and Technology Service Network Initiative, Chinese Academy of Sciences[KFJ-STS-QYZD-2021-11-001] ; Beijing Municipal Science & Technology Commission[Z211100002121171] ; Jinan ST Bureau[2020GXRC030]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems
WOS记录号	WOS:000877952100007
出版者	ASSOC COMPUTING MACHINERY
引用统计	被引频次：11[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19909
专题	中国科学院计算技术研究所期刊论文
通讯作者	Chen, Yiqiang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, 6 Kexueyuan South Rd, Beijing, Peoples R China 2.Univ Chinese Acad Sci, 19 Yuquan Rd, Beijing, Peoples R China 3.Peng Cheng Lab, Xingke 1st St, Shenzhen, Peoples R China 4.Shandong Acad Intelligent Comp Technol, Jinan, Peoples R China 5.Beijing Key Lab Mobile Comp & Pervas Device, Beijing, Peoples R China 6.Chinese Acad Sci, Bur Frontier Sci & Educ, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zeng, Bixiao,Yang, Xiaodong,Chen, Yiqiang,et al. CLC: A Consensus-based Label Correction Approach in Federated Learning[J]. ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY,2022,13(5):23.
APA	Zeng, Bixiao,Yang, Xiaodong,Chen, Yiqiang,Yu, Hanchao,&Zhang, Yingwei.(2022).CLC: A Consensus-based Label Correction Approach in Federated Learning.ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY,13(5),23.
MLA	Zeng, Bixiao,et al."CLC: A Consensus-based Label Correction Approach in Federated Learning".ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY 13.5(2022):23.