Federated Data Quality Assessment Approach: Robust Learning With Mixed Label Noise

doi:10.1109/TNNLS.2023.3306874

	Federated Data Quality Assessment Approach: Robust Learning With Mixed Label Noise
	Zeng, Bixiao 1; Yang, Xiaodong 1,2; Chen, Yiqiang 1,3,4; Yu, Hanchao 5; Hu, Chunyu 6; Zhang, Yingwei 1
	2023-08-31
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
页码	15
摘要	Federated learning (FL) has been an effective way to train a machine learning model distributedly, holding local data without exchanging them. However, due to the inaccessibility of local data, FL with label noise would be more challenging. Most existing methods assume only open-set or closed-set noise and correspondingly propose filtering or correction solutions, ignoring that label noise can be mixed in real-world scenarios. In this article, we propose a novel FL method to discriminate the type of noise and make the FL mixed noise-robust, named FedMIN. FedMIN employs a composite framework that captures local-global differences in multiparticipant distributions to model generalized noise patterns. By determining adaptive thresholds for identifying mixed label noise in each client and assigning appropriate weights during model aggregation, FedMIN enhances the performance of the global model. Furthermore, FedMIN incorporates a loss alignment mechanism using local and global Gaussian mixture models (GMMs) to mitigate the risk of revealing samplewise loss. Extensive experiments are conducted on several public datasets, which include the simulated FL testbeds, i.e., CIFAR-10, CIFAR-100, and SVHN, and the real-world ones, i.e., Camelyon17 and multiorgan nuclei challenge (MoNuSAC). Compared to FL benchmarks, FedMIN improves model accuracy by up to 9.9% due to its superior noise estimation capabilities.
关键词	Noise measurement Servers Task analysis Adaptation models Data models Data integrity Computers Data quality assessment federated learning (FL) noise-robust algorithm
DOI	10.1109/TNNLS.2023.3306874
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Plan of China[2021YFC2501202] ; National Natural Science Foundation of China[62202455] ; National Natural Science Foundation of China[61972383] ; Beijing Municipal Science and Technology Commission[Z211100002121171] ; Beijing Municipal Science and Technology Commission[Z221100002722009] ; China Scholarship Council[202204910370]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:001060588000001
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://119.78.100.204/handle/2XEOYT63/21388
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chen, Yiqiang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China 2.Shandong Acad Intelligent Comp Technol, Inst Comp Technol, Jinan, Peoples R China 3.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 4.Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Bur Frontier Sci & Educ, Beijing 100045, Peoples R China 6.Qilu Univ Technol, Shandong Acad Sci, Jinan 250353, Peoples R China
推荐引用方式 GB/T 7714	Zeng, Bixiao,Yang, Xiaodong,Chen, Yiqiang,et al. Federated Data Quality Assessment Approach: Robust Learning With Mixed Label Noise[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:15.
APA	Zeng, Bixiao,Yang, Xiaodong,Chen, Yiqiang,Yu, Hanchao,Hu, Chunyu,&Zhang, Yingwei.(2023).Federated Data Quality Assessment Approach: Robust Learning With Mixed Label Noise.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,15.
MLA	Zeng, Bixiao,et al."Federated Data Quality Assessment Approach: Robust Learning With Mixed Label Noise".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):15.