mlsanityData to 14 Oct 2026

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

arXiv 2303.10373 ↗First posted 18 Mar 2023cs.LG eess.SPcited by 8

Not on the map. Why?

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.

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

28 of 52 references.

References · 28

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  6. 2019Towards Federated Learning at Scale: System Designcited by 832
  7. 2019Agnostic Federated Learningcited by 456
  8. 2019Fair Resource Allocation in Federated Learningcited by 394
  9. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 352
  10. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 198
  11. 2019Federated Learning over Wireless Fading Channelscited by 183
  12. 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 103
16 more
  1. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 73
  2. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 62
  3. 2020An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guaranteecited by 62
  4. 2021Towards Fairness-Aware Federated Learningcited by 58
  5. 2017Rotting Banditscited by 57
  6. 2020Multi-Armed Bandit Based Client Scheduling for Federated Learningcited by 57
  7. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  8. 2019Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networkscited by 39
  9. 2020Bandit-based Communication-Efficient Client Selection Strategies for Federated Learningcited by 29
  10. 2020Federated Learning under Importance Samplingcited by 26
  11. 2019Learning in Restless Multi-Armed Bandits via Adaptive Arm Sequencing Rulescited by 15
  12. 2021Accelerated Gradient Descent Learning over Multiple Access Fading Channelscited by 14
  13. 2021Distributed Learning over Markovian Fading Channels for Stable Spectrum Accesscited by 13
  14. 2020MAB-based Client Selection for Federated Learning with Uncertain Resources in Mobile Networkscited by 11
  15. 2021Fast Federated Edge Learning with Overlapped Communication and Computation and Channel-Aware Fair Client Schedulingcited by 9
  16. 2021Learning in Restless Bandits under Exogenous Global Markov Processcited by 9

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 4.

8 papers.

  1. 2023Sparse Training for Federated Learning with Regularized Error Correctioncited by 2
  2. 2024Federated Learning for Data Market: Shapley-UCB for Seller Selection and Incentivescited by 1
  3. 2024BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocationcited by 1
  4. 2025PAUSE: Low-Latency and Privacy-Aware Active User Selection for Federated Learningcited by 1
  5. 2023A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systemscited by 0
  6. 2025Control-Optimized Deep Reinforcement Learning for Artificially Intelligent Autonomous Systemscited by 0
  7. 2025From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0cited by 0
  8. 2025Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learningcited by 0