WFSL: Warmup-Based Federated Sequential Learning
Arafeh, Mohamad Hammoud, Ahmad Guizani, Mohsen Mourad, Azzam Otrok, Hadi Ould-Slimane, Hakima Dziong, Zbigniew Wang, Chang-Dong Wu, Di
Arafeh, Mohamad
Hammoud, Ahmad
Guizani, Mohsen
Mourad, Azzam
Otrok, Hadi
Ould-Slimane, Hakima
Dziong, Zbigniew
Wang, Chang-Dong
Wu, Di
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Federated learning (FL) gained importance in sensitive Internet of Things (IoT) environments by creating a privacy-preserving ecosystem where participants share machine-learning models instead of raw data. However, FL shifts data control away from the server, exposing it to non-independent and identically distributed (non-IID) problems caused by biased clients (IoT devices). This hinders the learning process by increasing execution time and cost. Current solutions alter the FL structure or compromise privacy by offloading clients' raw data to an external server. To mitigate these limitations, this article proposes a solution to the non-IID problem by introducing an initialization phase, orchestrated by the server, that constructs high-quality initial models. These models can boost FL accuracy and convergence, regardless of whether IoT participants exhibit non-IID properties. Our proposed initialization scheme involves clients training over the same model sequentially, lessening the impact of aggregation, a primary cause of model degradation in federated approaches. Furthermore, a regulator algorithm deployed on the server maintains model integrity and mitigates catastrophic forgetting, enhanced by a client selection process that emphasizes the compatibility of IoT clients to cooperate effectively. Moreover, we devise an optimization scheme based on clustering and genetic algorithms to reduce the selection time while ensuring optimal performance in IoT networks. Experiments on MNIST, KDD, and CIFAR10 data sets show promising results in terms of initial model resiliency against catastrophic forgetting and non-IID settings. Additionally, our findings suggest that our approach can significantly enhance FL training in IoT applications by achieving 40% higher initialization accuracy and a 20% average improvement in end results compared to conventional methods, all while reducing computation time by 80% compared to similar approaches.
Citation
M. Arafeh et al., “WFSL: Warmup-Based Federated Sequential Learning,” IEEE Internet Things J, 2024, doi: 10.1109/JIOT.2024.3467110.
Source
IEEE Internet of Things Journal
Conference
Keywords
Catastrophic forgetting, federated learning (FL), Internet of Things (IoT), non-independent, identically distributed (non-IID) problem, sequential learning
Subjects
Source
Publisher
IEEE