Mobility-Aware Cluster Federated Learning in Hierarchical Wireless Networks

Implementing federated learning (FL) algorithms in wireless networks has garnered a wide range of attention. However, few works have considered the impact of user mobility on the learning performance. To fill this research gap, we develop a theoretical model to characterize the hierarchical federate...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on wireless communications Vol. 21; no. 10; pp. 8441 - 8458
Main Authors: Feng, Chenyuan, Yang, Howard H., Hu, Deshun, Zhao, Zhiwei, Quek, Tony Q. S., Min, Geyong
Format: Journal Article
Language:English
Published: New York IEEE 01.10.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Clustering algorithms
Clusters
Collaborative work
Convergence
convergence analysis
data heterogeneity
Data models
Federated learning
Hierarchical federated learning
Machine learning
Performance evaluation
Servers
Training
user mobility
Wireless networks
ISSN:1536-1276, 1558-2248
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Implementing federated learning (FL) algorithms in wireless networks has garnered a wide range of attention. However, few works have considered the impact of user mobility on the learning performance. To fill this research gap, we develop a theoretical model to characterize the hierarchical federated learning (HFL) algorithm in wireless networks where the mobile users may roam across edge access points (APs), leading to incompletion of inconsistent FL training. We provide the convergence analysis of conventional HFL with user mobility. Our analysis proves that the learning performance of conventional HFL deteriorates drastically with highly-mobile users. And such a decline in the learning performance will be exacerbated with small number of participants and large data distribution divergences among users' local data. To circumvent these issues, we propose a mobility-aware cluster federated learning (MACFL) algorithm by redesigning the access mechanism, local update rule, and model aggregation scheme. We also conduct experiments to evaluate the learning performance of conventional HFL, a cluster federated learning (CFL) with simple averaging, and our proposed MACFL. The results show that our MACFL can enhance the learning performance, especially for three different cases: (<inline-formula> <tex-math notation="LaTeX">i </tex-math></inline-formula>) the case of users with non-independent and identically distributed (non-IID) data, (<inline-formula> <tex-math notation="LaTeX">ii </tex-math></inline-formula>) the case of users with high mobility, and (<inline-formula> <tex-math notation="LaTeX">iii </tex-math></inline-formula>) the case with a small number of users.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1536-1276
1558-2248
DOI:10.1109/TWC.2022.3166386