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

TL;DR

FLASH-RL is a novel federated learning framework that uses reinforcement learning to optimize client selection, effectively balancing system heterogeneity, reducing latency, and accelerating training on multiple datasets.

Contribution

It introduces a reinforcement learning-based client selection method with a reputation utility function, addressing system and static heterogeneity in federated learning.

Findings

Reduces latency by up to 24.83% compared to FedAVG.

Cuts training rounds by up to 60.44% over FedAVG.

Improves model performance and training speed in fall detection.

Abstract

Federated Learning (FL) has emerged as a promising Machine Learning paradigm, enabling multiple users to collaboratively train a shared model while preserving their local data. To minimize computing and communication costs associated with parameter transfer, it is common practice in FL to select a subset of clients in each training round. This selection must consider both system and static heterogeneity. Therefore, we propose FLASH-RL, a framework that utilizes Double Deep QLearning (DDQL) to address both system and static heterogeneity in 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 have shown FLASH-RL's effectiveness in achieving a balanced trade-off between model performance and end-to-end latency against existing solutions. Indeed, FLASH-RL reduces latency by up to 24.83% compared to FedAVG and 24.67% compared to FAVOR. It also reduces the training rounds by up to 60.44% compared to FedAVG and +76% compared to FAVOR. In fall detection using the MobiAct dataset, FLASH-RL outperforms FedAVG by up to 2.82% in model's performance and reduces latency by up to 34.75%. Additionally, FLASH-RL achieves the target performance faster, with up to a 45.32% reduction in training rounds compared to FedAVG.