CroSSHeteroFL: Cross-Stratified Sampling Composition-Fitting to Federated Learning for Heterogeneous Clients

In the large-scale deployment of federated learning (FL) systems, the heterogeneity of clients, such as mobile phones and Internet of Things (IoT) devices with different configurations, constitutes a significant problem regarding fairness, training performance, and accuracy. Such system heterogeneit...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024, Vol.12, p.148011-148025
Main Authors: Tinh, Vo Phuc, Son, Hoang Hai, Nam, Nguyen Hoang, Dang, Duc Ngoc Minh, Le, Duy-Dong, Nguyen, Thai-Binh, Pham, Thanh-Qui, Nguyen, van-Luong, Huynh, Duy-Thanh, Khoa, Tran Anh
Format: Article
Language:English
Subjects:
Adaptation models
capability
computation complexity
Computational complexity
Computational modeling
Computer architecture
Data models
Federated learning
heterogeneity
Internet of Things
Noise measurement
resource-adaptive
Servers
Training
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the large-scale deployment of federated learning (FL) systems, the heterogeneity of clients, such as mobile phones and Internet of Things (IoT) devices with different configurations, constitutes a significant problem regarding fairness, training performance, and accuracy. Such system heterogeneity leads to an inevitable trade-off between model complexity and data accessibility as a bottleneck. To avoid this situation and to achieve resource-adaptive FL, we introduce CrossHeteroFL to deal with heterogeneous clients equipped with different computational and communication capabilities. Our solution enables the training of heterogeneous local models with additional computational complexity and still generates a single global inference model. We demonstrate several CrossHeteroFL training scenarios and conduct extensive empirical evaluation, covering four levels of the computational complexity of three-model architectures on two datasets. The proposed mechanism provides the system with non-elementary access to a scattered fit among clients. However, the proposed method generalizes soft handover-based solutions by adjusting the model width according to clients' capabilities and a tiered balance of data-source overviews to assess clients' interests accurately. The evaluation results indicate our method solves the challenges in previous studies and produces greater top-1 accuracy and consistent performance under heterogeneous client conditions.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3475737