中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
CLC: A Consensus-based Label Correction Approach in Federated Learning

文献类型：期刊论文

作者Zeng, Bixiao4,5,6; Yang, Xiaodong3,6; Chen, Yiqiang2,4,5,6; Yu, Hanchao1; Zhang, Yingwei6
刊名ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
出版日期2022-10-01
卷号13期号:5页码:23
关键词Federated learning data evaluation consensus mechanism
ISSN号2157-6904
DOI10.1145/3519311
英文摘要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.
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
语种英语
WOS记录号WOS:000877952100007
出版者ASSOC COMPUTING MACHINERY
源URL[http://119.78.100.204/handle/2XEOYT63/19908]  
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, Bur Frontier Sci & Educ, Beijing, Peoples R China
2.Beijing Key Lab Mobile Comp & Pervas Device, Beijing, Peoples R China
3.Shandong Acad Intelligent Comp Technol, Jinan, Peoples R China
4.Peng Cheng Lab, Xingke 1st St, Shenzhen, Peoples R China
5.Univ Chinese Acad Sci, 19 Yuquan Rd, Beijing, Peoples R China
6.Chinese Acad Sci, Inst Comp Technol, 6 Kexueyuan South Rd, 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.

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。