A Survey on Participant Selection for Federated Learning in Mobile Networks

TL;DR

This survey reviews various participant selection techniques in federated learning over mobile networks, emphasizing their importance in optimizing model accuracy and training efficiency amidst device heterogeneity and communication constraints.

Contribution

It categorizes existing participant selection methods for federated learning and discusses future research directions in this domain.

Findings

Identifies key challenges in participant selection for FL.

Classifies existing solutions based on their approaches.

Highlights future research directions.

Abstract

Federated Learning (FL) is an efficient distributed machine learning paradigm that employs private datasets in a privacy-preserving manner. The main challenges of FL is that end devices usually possess various computation and communication capabilities and their training data are not independent and identically distributed (non-IID). Due to limited communication bandwidth and unstable availability of such devices in a mobile network, only a fraction of end devices (also referred to as the participants or clients in a FL process) can be selected in each round. Hence, it is of paramount importance to utilize an efficient participant selection scheme to maximize the performance of FL including final model accuracy and training time. In this paper, we provide a review of participant selection techniques for FL. First, we introduce FL and highlight the main challenges during participant selection. Then, we review the existing studies and categorize them based on their solutions. Finally, we provide some future directions on participant selection for FL based on our analysis of the state-of-the-art in this topic area.