Federated Data Quality Assessment Approach: Robust Learning With Mixed Label Noise
文献类型：期刊论文
| 作者 | Zeng, Bixiao4; Yang, Xiaodong4,5; Chen, Yiqiang1,4,6; Yu, Hanchao3; Hu, Chunyu2; Zhang, Yingwei4 |
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2023-08-31 |
| 页码 | 15 |
| 关键词 | Noise measurement Servers Task analysis Adaptation models Data models Data integrity Computers Data quality assessment federated learning (FL) noise-robust algorithm |
| ISSN号 | 2162-237X |
| DOI | 10.1109/TNNLS.2023.3306874 |
| 英文摘要 | 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. |
| 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 |
| 语种 | 英语 |
| WOS记录号 | WOS:001060588000001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/21387]  |
| 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.Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China 2.Qilu Univ Technol, Shandong Acad Sci, Jinan 250353, Peoples R China 3.Chinese Acad Sci, Bur Frontier Sci & Educ, Beijing 100045, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China 5.Shandong Acad Intelligent Comp Technol, Inst Comp Technol, Jinan, Peoples R China 6.Univ Chinese Acad Sci, Beijing 101408, 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. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。