mlsanityData to 7 Oct 2026

Federated Multi-armed Bandits with Personalization

arXiv 2102.13101 ↗First posted 25 Feb 2021cs.LG cs.IT math.ITcited by 62

Not on the map. Why?

Abstract (arXiv)

A general framework of personalized federated multi-armed bandits (PF-MAB) is proposed, which is a new bandit paradigm analogous to the federated learning (FL) framework in supervised learning and enjoys the features of FL with personalization. Under the PF-MAB framework, a mixed bandit learning problem that flexibly balances generalization and personalization is studied. A lower bound analysis for the mixed model is presented. We then propose the Personalized Federated Upper Confidence Bound (PF-UCB) algorithm, where the exploration length is chosen carefully to achieve the desired balance of learning the local model and supplying global information for the mixed learning objective. Theoretical analysis proves that PF-UCB achieves an O(log(T)) regret regardless of the degree of personalization, and has a similar instance dependency as the lower bound. Experiments using both synthetic and real-world datasets corroborate the theoretical analysis and demonstrate the effectiveness of the proposed algorithm.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Builds on 22 of its 35 references that are in the map. First posted on arXiv 25 Feb 2021.

Builds on

22 of 35 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  4. 2019Towards Federated Learning at Scale: System Designcited by 826
  5. 2017Federated Multi-Task Learningcited by 669
  6. 2020Adaptive Personalized Federated Learningcited by 353
  7. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
  8. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  9. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  10. 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
  11. 2019Federated Evaluation of On-device Personalizationcited by 147
  12. 2020Survey of Personalization Techniques for Federated Learningcited by 144
10 more
  1. 2020Differentially-Private Federated Linear Banditscited by 83
  2. 2021Federated Multi-Armed Banditscited by 59
  3. 2020Federated Bandit: A Gossiping Approachcited by 55
  4. 2018SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Banditscited by 46
  5. 2015On Distributed Cooperative Decision-Making in Multiarmed Banditscited by 33
  6. 2020Federated Recommendation System via Differential Privacycited by 26
  7. 2019A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Playerscited by 25
  8. 2020Decentralized Multi-player Multi-armed Bandits with No Collision Informationcited by 25
  9. 2020Federated Residual Learningcited by 23
  10. 2019Multiplayer Bandit Learning, from Competition to Cooperationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 22; 2023: 19; 2024: 6; 2025: 5; 2026: 1.

62 papers.

Sort:

By area:

  1. 2021Federated Linear Contextual Banditscited by 61
  2. 2021Fault-Tolerant Federated Reinforcement Learning with Theoretical Guaranteecited by 52
  3. 2021Differentially Private Federated Bayesian Optimization with Distributed Explorationcited by 32
  4. 2021Exploiting Heterogeneity in Robust Federated Best-Arm Identificationcited by 20
  5. 2021Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligencecited by 18
  6. 2022Near-Optimal Collaborative Learning in Banditscited by 18
  7. 2022Federated Neural Banditscited by 17
  8. 2022Communication Efficient Federated Learning for Generalized Linear Banditscited by 13
  9. 2023Federated Linear Contextual Bandits with User-level Differential Privacycited by 12
  10. 2021Privacy-Preserving Communication-Efficient Federated Multi-Armed Banditscited by 11
  11. 2022Almost Cost-Free Communication in Federated Best Arm Identificationcited by 11
  12. 2023Federated Multi-Objective Learningcited by 11
38 more
  1. 2022Linear Stochastic Bandits over a Bit-Constrained Channelcited by 9
  2. 2022Differentially Private Linear Bandits with Partial Distributed Feedbackcited by 8
  3. 2022Federated Best Arm Identification with Heterogeneous Clientscited by 8
  4. 2022Distributed Linear Bandits under Communication Constraintscited by 8
  5. 2022Byzantine-Robust Federated Linear Banditscited by 7
  6. 2023Doubly Adversarial Federated Banditscited by 7
  7. 2023Federated Online and Bandit Convex Optimizationcited by 7
  8. 2022Federated Multi-Armed Bandits Under Byzantine Attackscited by 6
  9. 2022Collaborative Learning in Kernel-based Bandits for Distributed Userscited by 6
  10. 2022Parallel Best Arm Identification in Heterogeneous Environmentscited by 6
  11. 2023On-Demand Communication for Asynchronous Multi-Agent Banditscited by 6
  12. 2023Pure Exploration in Asynchronous Federated Banditscited by 6
  13. 2022Federated X-Armed Banditcited by 5
  14. 2022Communication-Efficient Collaborative Best Arm Identificationcited by 5
  15. 2022Collaborative Algorithms for Online Personalized Mean Estimationcited by 5
  16. 2021Accelerating Federated Learning with a Global Biased Optimisercited by 4
  17. 2022Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Boundscited by 4
  18. 2022Adaptive Expert Models for Personalization in Federated Learningcited by 4
  19. 2021(Almost) Free Incentivized Exploration from Decentralized Learning Agentscited by 3
  20. 2022Federated Online Sparse Decision Makingcited by 3
  21. 2022Differentially Private Federated Combinatorial Bandits with Constraintscited by 3
  22. 2022Lifelong Bandit Optimization: No Prior and No Regretcited by 3
  23. 2023Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costscited by 3
  24. 2023Incentivized Communication for Federated Banditscited by 3
  25. 2023Byzantine-Resilient Decentralized Multi-Armed Banditscited by 3
  26. 2023Federated Linear Bandits with Finite Adversarial Actionscited by 3
  27. 2021Decentralized Upper Confidence Bound Algorithms for Homogeneous Multi-Agent Multi-Armed Banditscited by 2
  28. 2022One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learningcited by 2
  29. 2023Communication-Efficient Collaborative Regret Minimization in Multi-Armed Banditscited by 2
  30. 2025Federated Linear Dueling Banditscited by 2
  31. 2023Federated Learning for Heterogeneous Bandits with Unobserved Contextscited by 1
  32. 2023Large-Scale Distributed Learning via Private On-Device Locality-Sensitive Hashingcited by 1
  33. 2023Harnessing the Power of Federated Learning in Federated Contextual Banditscited by 1
  34. 2024Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-upscited by 1
  35. 2024Differentially-Private Collaborative Online Personalized Mean Estimationcited by 1
  36. 2024BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocationcited by 1
  37. 2026Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applicationscited by 1
  38. 2022Vertical Federated Linear Contextual Banditscited by 0

50 most cited of 62 All 62 (JSON)