首页|期刊导航|防务技术|Controlling update distance and enhancing fair trainable prototypes in federated learning under data and model heterogeneity

Controlling update distance and enhancing fair trainable prototypes in federated learning under data and model heterogeneity

Kangning Yin Zhen Ding Xinhui Ji Zhiguo Wang

防务技术2025，Vol.47Issue(5)：15-31,17.

防务技术2025，Vol.47Issue(5)：15-31,17.DOI:10.1016/j.dt.2024.12.024

Controlling update distance and enhancing fair trainable prototypes in federated learning under data and model heterogeneity

Kangning Yin ¹Zhen Ding ²Xinhui Ji ³Zhiguo Wang²

作者信息

1. School of Information and Software Engineering,University of Electronic Science and Technology of China,Chengdu 610054,China||Institute of Public Security,Kash Institute of Electronics and Information Industry,Kash 844000,China
2. School of Information and Software Engineering,University of Electronic Science and Technology of China,Chengdu 610054,China
3. Shanghai New Energy Vehicle Public Data Collection and Monitoring Research Center,Shanghai 200241,China
折叠

摘要

关键词

Heterogeneous federated learning/Model heterogeneity/Data heterogeneity/Contrastive learning

Key words

Heterogeneous federated learning/Model heterogeneity/Data heterogeneity/Contrastive learning

引用本文复制引用

Kangning Yin,Zhen Ding,Xinhui Ji,Zhiguo Wang..Controlling update distance and enhancing fair trainable prototypes in federated learning under data and model heterogeneity[J].防务技术,2025,47(5):15-31,17.

基金项目

This work was supported by the Natural Science Foundation of Xinjiang Uygur Autonomous Region(No.2022D01B187). （No.2022D01B187）

防务技术

ISSN：2214-9147

访问量0

下载量0

段落导航