Resource-Efficient Federated Learning

TL;DR

This paper explores resource-efficient federated learning by proposing intelligent participant selection and update incorporation, which improve model quality and resource use amid data heterogeneity and participant variability.

Contribution

It introduces novel strategies for participant selection and update handling that enhance resource efficiency and model performance in federated learning.

Findings

Improved model accuracy with resource-aware participant selection.

Enhanced efficiency by incorporating straggling participants' updates.

Better handling of data heterogeneity and device variability.

Abstract

Federated Learning (FL) enables distributed training by learners using local data, thereby enhancing privacy and reducing communication. However, it presents numerous challenges relating to the heterogeneity of the data distribution, device capabilities, and participant availability as deployments scale, which can impact both model convergence and bias. Existing FL schemes use random participant selection to improve fairness; however, this can result in inefficient use of resources and lower quality training. In this work, we systematically address the question of resource efficiency in FL, showing the benefits of intelligent participant selection, and incorporation of updates from straggling participants. We demonstrate how these factors enable resource efficiency while also improving trained model quality.