# Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach

arXiv: https://arxiv.org/abs/2303.10373 · HTML: https://mlsanity.com/paper/2303.10373/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 52 references that are in the map.
- First posted on arXiv 18 Mar 2023.

## Builds on (most cited first, 28 of 28)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge](https://mlsanity.com/paper/1804.08333/) (2018)
- [Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies](https://mlsanity.com/paper/2010.01243/) (2020)
- [Federated Learning over Wireless Fading Channels](https://mlsanity.com/paper/1907.09769/) (2019)
- [Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective](https://mlsanity.com/paper/2004.04314/) (2020)
- [Over-the-Air Federated Learning from Heterogeneous Data](https://mlsanity.com/paper/2009.12787/) (2020)
- [On Analog Gradient Descent Learning over Multiple Access Fading Channels](https://mlsanity.com/paper/1908.07463/) (2019)
- [An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee](https://mlsanity.com/paper/2011.01783/) (2020)
- [Towards Fairness-Aware Federated Learning](https://mlsanity.com/paper/2111.01872/) (2021)
- [Rotting Bandits](https://mlsanity.com/paper/1702.07274/) (2017)
- [Multi-Armed Bandit Based Client Scheduling for Federated Learning](https://mlsanity.com/paper/2007.02315/) (2020)
- [Federated Learning: A Signal Processing Perspective](https://mlsanity.com/paper/2103.17150/) (2021)
- [Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networks](https://mlsanity.com/paper/1910.14648/) (2019)
- [Bandit-based Communication-Efficient Client Selection Strategies for Federated Learning](https://mlsanity.com/paper/2012.08009/) (2020)
- [Federated Learning under Importance Sampling](https://mlsanity.com/paper/2012.07383/) (2020)
- [Learning in Restless Multi-Armed Bandits via Adaptive Arm Sequencing Rules](https://mlsanity.com/paper/1906.08120/) (2019)
- [Accelerated Gradient Descent Learning over Multiple Access Fading Channels](https://mlsanity.com/paper/2107.12452/) (2021)
- [Distributed Learning over Markovian Fading Channels for Stable Spectrum Access](https://mlsanity.com/paper/2101.11292/) (2021)
- [MAB-based Client Selection for Federated Learning with Uncertain Resources in Mobile Networks](https://mlsanity.com/paper/2009.13879/) (2020)
- [Fast Federated Edge Learning with Overlapped Communication and Computation and Channel-Aware Fair Client Scheduling](https://mlsanity.com/paper/2109.06710/) (2021)
- [Learning in Restless Bandits under Exogenous Global Markov Process](https://mlsanity.com/paper/2112.09484/) (2021)

## Built on by (most cited first, 8 of 8)

- [Sparse Training for Federated Learning with Regularized Error Correction](https://mlsanity.com/paper/2312.13795/) (2023)
- [Federated Learning for Data Market: Shapley-UCB for Seller Selection and Incentives](https://mlsanity.com/paper/2410.09107/) (2024)
- [BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation](https://mlsanity.com/paper/2412.02934/) (2024)
- [PAUSE: Low-Latency and Privacy-Aware Active User Selection for Federated Learning](https://mlsanity.com/paper/2503.13173/) (2025)
- [A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems](https://mlsanity.com/paper/2312.03889/) (2023)
- [Control-Optimized Deep Reinforcement Learning for Artificially Intelligent Autonomous Systems](https://mlsanity.com/paper/2507.00268/) (2025)
- [From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0](https://mlsanity.com/paper/2507.15796/) (2025)
- [Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learning](https://mlsanity.com/paper/2512.24959/) (2025)

## Abstract (arXiv)

Federated learning (FL) is an emerging machine learning (ML) paradigm used to train models across multiple nodes (i.e., clients) holding local data sets, without explicitly exchanging the data. It has attracted a growing interest in recent years due to its advantages in terms of privacy considerations, and communication resources. In FL, selected clients train their local models and send a function of the models to the server, which consumes a random processing and transmission time. The server updates the global model and broadcasts it back to the clients. The client selection problem in FL is to schedule a subset of the clients for training and transmission at each given time so as to optimize the learning performance. In this paper, we present a novel multi-armed bandit (MAB)-based approach for client selection to minimize the training latency without harming the ability of the model to generalize, that is, to provide reliable predictions for new observations. We develop a novel algorithm to achieve this goal, dubbed Bandit Scheduling for FL (BSFL). We analyze BSFL theoretically, and show that it achieves a logarithmic regret, defined as the loss of BSFL as compared to a genie that has complete knowledge about the latency means of all clients. Furthermore, simulation results using synthetic and real datasets demonstrate that BSFL is superior to existing methods.