Bandit-Based Sequential Client Scheduling in Federated Learning

Ben-Ami, Dan; Cohen, Kobi; Zhao, Qing

Permalink

https://hdl.handle.net/2142/130266 Copy

Description

Title

Bandit-Based Sequential Client Scheduling in Federated Learning

Author(s)

• Ben-Ami, Dan
• Cohen, Kobi
• Zhao, Qing

Issue Date

2025-09-17

Keyword(s)

• Federated learning(FL)
• Scheduling
• Multi-armed bandit(MAB)
• Sequential decision making

Abstract

Federated learning (FL) enables distributed model training across multiple clients without sharing raw data, preserving privacy and reducing communication overhead. A key challenge in FL is sequentially scheduling clients for training and transmission to balance generalization performance with latency constraints. In this work, we address this challenge through a multi-armed bandit (MAB) framework that models client scheduling as a sequential decision-making problem. We propose a novel MAB approach for sequential client scheduling in FL, designed to minimize training latency without compromising model generalization, the ability to make accurate predictions on unseen data. Building on this framework, we develop a low-complexity algorithm that efficiently balances this trade-off. We prove that the algorithm achieves logarithmic regret over time, relative to an oracle with full knowledge of client latency means. Experimental results on both synthetic and real-world datasets demonstrate that our method consistently outperforms existing client selection strategies in terms of convergence speed and generalization performance.

Publisher

Allerton Conference on Communication, Control, and Computing

Series/Report Name or Number

2025 61st Allerton Conference on Communication, Control, and Computing Proceedings

ISSN

2836-4503

Type of Resource

Text

Genre of Resource

Conference Paper/Presentation

Language

eng

Handle URL

https://hdl.handle.net/2142/130266&&

Copyright and License Information

Copyright 2025 owned by the authors.

Owning Collections