Learn More by Using Less: Distributed Learning with Energy-Constrained Devices

TL;DR

This paper introduces LeanFed, an energy-aware federated learning framework that optimizes client participation and data usage on battery-limited devices, improving model accuracy and stability in resource-constrained environments.

Contribution

The paper presents LeanFed, a novel adaptive data usage method for energy-constrained federated learning, enhancing participation and accuracy on devices with limited battery life.

Findings

LeanFed improves model accuracy over traditional methods.

It reduces client dropout and extends device participation.

Performance gains are significant in high heterogeneity scenarios.

Abstract

Federated Learning (FL) has emerged as a solution for distributed model training across decentralized, privacy-preserving devices, but the different energy capacities of participating devices (system heterogeneity) constrain real-world implementations. These energy limitations not only reduce model accuracy but also increase dropout rates, impacting on convergence in practical FL deployments. In this work, we propose LeanFed, an energy-aware FL framework designed to optimize client selection and training workloads on battery-constrained devices. LeanFed leverages adaptive data usage by dynamically adjusting the fraction of local data each device utilizes during training, thereby maximizing device participation across communication rounds while ensuring they do not run out of battery during the process. We rigorously evaluate LeanFed against traditional FedAvg on CIFAR-10 and CIFAR-100 datasets, simulating various levels of data heterogeneity and device participation rates. Results show that LeanFed consistently enhances model accuracy and stability, particularly in settings with high data heterogeneity and limited battery life, by mitigating client dropout and extending device availability. This approach demonstrates the potential of energy-efficient, privacy-preserving FL in real-world, large-scale applications, setting a foundation for robust and sustainable pervasive AI on resource-constrained networks.