GHPFL: Advancing Personalized Edge-Based Learning through Optimized Bandwidth Utilization
Mo, Kaiwei Lin, Wei Lu, Jiaxun Xue, Chun Jason Shao, Yunfeng Xu, Hong
Mo, Kaiwei
Lin, Wei
Lu, Jiaxun
Xue, Chun Jason
Shao, Yunfeng
Xu, Hong
Supervisor
Department
Computer Science
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Federated learning (FL) is increasingly adopted to combine knowledge from clients in training without revealing their private data. In order to improve the performance of different participants, personalized FL has recently been proposed. However, considering the non-independent and identically distributed (non-IID) data and limited bandwidth at clients, the model performance could be compromised. In reality, clients near each other often tend to have similar data distributions. In this work, we train the personalized edge-based model in the client-edge-server FL. While considering the differences in data distribution, we fully utilize the limited bandwidth resources. To make training efficient and accurate at the same time, An intuitive idea is to learn as much useful knowledge as possible from other edges and reduce the accuracy loss incurred by non-IID data. Therefore, we devise Grouping Hierarchical Personalized Federated Learning (GHPFL). In this framework, each edge establishes physical connections with multiple clients, while the server physically connects with edges. It clusters edges into groups and establishes client-edge logical connections for synchronization. This is based on data similarities that the nodes actively identify, as well as the underlying physical topology. We perform a large-scale evaluation to demonstrate GHPFL's benefits over other schemes.
Citation
K. Mo, W. Lin, J. Lu, C. J. Xue, Y. Shao and H. Xu, "GHPFL: Advancing Personalized Edge-Based Learning through Optimized Bandwidth Utilization," in IEEE Transactions on Cloud Computing, doi: 10.1109/TCC.2025.3540023.
Source
IEEE Transactions on Cloud Computing
Conference
Keywords
Federated learning, Servers, Training, Data models, Accuracy, B, width, Cloud computing, Adaptation models, Load modeling, Interpolation
Subjects
Source
Publisher
IEEE