Federated Learning with Downlink Device Selection

TL;DR

This paper explores a federated learning framework that selects devices based on downlink channel conditions, optimizing partial participation to improve model accuracy and efficiency in wireless edge networks.

Contribution

It introduces a novel device selection method based on downlink channels and designs a partial participation scheme with quantized model updates for federated learning.

Findings

Partial device participation improves model accuracy over full participation.

Optimal number of participating devices depends on channel conditions and dataset bias.

Quantized updates enable efficient communication with maintained convergence.

Abstract

We study federated edge learning, where a global model is trained collaboratively using privacy-sensitive data at the edge of a wireless network. A parameter server (PS) keeps track of the global model and shares it with the wireless edge devices for training using their private local data. The devices then transmit their local model updates, which are used to update the global model, to the PS. The algorithm, which involves transmission over PS-to-device and device-to-PS links, continues until the convergence of the global model or lack of any participating devices. In this study, we consider device selection based on downlink channels over which the PS shares the global model with the devices. Performing digital downlink transmission, we design a partial device participation framework where a subset of the devices is selected for training at each iteration. Therefore, the participating devices can have a better estimate of the global model compared to the full device participation case which is due to the shared nature of the broadcast channel with the price of updating the global model with respect to a smaller set of data. At each iteration, the PS broadcasts different quantized global model updates to different participating devices based on the last global model estimates available at the devices. We investigate the best number of participating devices through experimental results for image classification using the MNIST dataset with biased distribution.