Adaptive Federated Learning With Non-IID Data
文献类型:期刊论文
作者 | Zeng, Yan3,4,5; Mu, Yuankai2; Yuan, Junfeng5; Teng, Siyuan5; Zhang, Jilin3,4,5; Wan, Jian3,4,5; Ren, Yongjian3,4,5; Zhang, Yunquan1 |
刊名 | COMPUTER JOURNAL |
出版日期 | 2022-09-30 |
页码 | 15 |
ISSN号 | 0010-4620 |
关键词 | Federated Learning Model Aggregation Non-IID |
DOI | 10.1093/comjnl/bxac118 |
英文摘要 | With the widespread use of Internet of things(IoT) devices, it generates an enormous volume of data, and it is a challenge to mine the IoT data value while ensuring security and privacy. Federated learning is a decentralized approach for training data located on edge devices, such as mobile phones and IoT devices, while keeping privacy, efficiency, and security. However, the Non-IID (non-independent and identically distributed) data, always greatly impacts the performance of the global model. In this paper, we propose a FedDynamic algorithm to solve the statistical challenge of federated learning caused by Non-IID. As Non-IID data can lead to significant differences in model parameters between edge devices, we set different weights for different devices during model aggregation to get a high-performance global model. We analyze and exact key indices (local model accuracy, local data quality, and model difference between local models and the global model), which can reflect the quality of the model, and calculate the aggregation weight for edge devices based on the key indices. Furthermore, we dynamically adjust aggregation weight based on accuracy's variety to solve weight staleness during the training process. Experiments on the MNIST, FMNIST, EMNIST, CINIC-10 and CIFAR-10 datasets show that the FedDynamic algorithm has better accuracy and convergence performance, compared to the FedAvg, FedProx and Scaffold algorithms. |
资助项目 | Technology Research and Development Program of China[2019YFB2102100] ; National Natural Science Foundation of China[62072146] ; National Natural Science Foundation of China[61972358] ; Key Research and Development Program of Zhejiang Province[2021C03187] ; Key Research and Development Program of Zhejiang Province[2019C03134] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | OXFORD UNIV PRESS |
WOS记录号 | WOS:000862225700001 |
源URL | [http://119.78.100.204/handle/2XEOYT63/19814] |
专题 | 中国科学院计算技术研究所期刊论文 |
通讯作者 | Wan, Jian; Ren, Yongjian |
作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, Beijing 100086, Peoples R China 2.Hangzhou Dianzi Univ, HDU ITMO Joint Inst, Hangzhou 310018, Peoples R China 3.Zhejiang Engn Res Ctr Data Secur Governance, Hangzhou 310018, Peoples R China 4.Minist Educ, Key Lab Complex Syst Modeling & Simulat, Hangzhou 310018, Peoples R China 5.Hangzhou Dianzi Univ, Sch Comp Sci & Technol, Hangzhou 310018, Peoples R China |
推荐引用方式 GB/T 7714 | Zeng, Yan,Mu, Yuankai,Yuan, Junfeng,et al. Adaptive Federated Learning With Non-IID Data[J]. COMPUTER JOURNAL,2022:15. |
APA | Zeng, Yan.,Mu, Yuankai.,Yuan, Junfeng.,Teng, Siyuan.,Zhang, Jilin.,...&Zhang, Yunquan.(2022).Adaptive Federated Learning With Non-IID Data.COMPUTER JOURNAL,15. |
MLA | Zeng, Yan,et al."Adaptive Federated Learning With Non-IID Data".COMPUTER JOURNAL (2022):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。