FLASH-RL: Federated Learning Addressing System and Static Heterogeneity using Reinforcement Learning

We propose FLASH-RL, a framework utilizing Double Deep Q-Learning (DDQL) to address system and static heterogeneity in Federated Learning (FL). FLASH-RL introduces a new reputation-based utility function to evaluate client contributions based on their current and past performances. Additionally, an...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE 41st International Conference on Computer Design (ICCD) pp. 444 - 447
Main Authors Bouaziz, Sofiane, Benmeziane, Hadjer, Imine, Youcef, Hamdad, Leila, Niar, Smail, Ouarnoughi, Hamza
Format Conference Proceeding
LanguageEnglish
Published IEEE 06.11.2023
Subjects
Client selection
Federated Learning
Reinforcement Learning
Static heterogeneity
System heterogeneity
Online AccessGet full text

Cover

More Information
Summary:We propose FLASH-RL, a framework utilizing Double Deep Q-Learning (DDQL) to address system and static heterogeneity in Federated Learning (FL). FLASH-RL introduces a new reputation-based utility function to evaluate client contributions based on their current and past performances. Additionally, an adapted DDQL algorithm is proposed to expedite the learning process. Experimental results on MNIST and CIFAR-10 datasets demonstrate that FLASH-RL strikes a balance between model performance and end-to-end latency, reducing latency by up to 24.83% compared to FedAVG and 24.67% compared to FAVOR. It also reduces training rounds by up to 60.44% compared to FedAVG and 76% compared to FAVOR. Similar improvements are observed on the MobiAct Dataset for fall detection, underscoring the real-world applicability of our approach.
ISSN:2576-6996
DOI:10.1109/ICCD58817.2023.00074