DOI number:10.1109/TNSE.2024.3447904
Affiliation of Author(s):杭州国际创新研究院
Journal:IEEE Transactions on Network Science and Engineering
Place of Publication:美国
Key Words:hierarchical federated learning; data heterogeneity; aggregation weights; mobile edge computing; resource optimization
Abstract:针对无线网络中的层次化联邦学习，分析MEC内独立同分布、MEC间非独立同分布数据条件下的数据异质性影响，推导训练损失上界。提出FedHelo算法，在时延和客户端能耗约束下联合优化聚合权重以及边缘和全局聚合频率。
Note:Early Access日期为2024-08-26；正式刊期为2024年11卷6期。
Co-author:Youjia Chen, Junnan Yang, Ming Ding, Peng Cheng, Haifeng Zheng
First Author:Yuchuan Ye
Indexed by:Journal paper
Document Code:10646590
Discipline:工学
First-Level Discipline:Information and Communication Engineering
Document Type:SCI
Volume:11
Issue:6
Page Number:6066-6079
ISSN No.:2327-4697; 2334-329X
Translation or Not:no
Date of Publication:2024-08-26