mlsanityData to 14 Oct 2026

Federated Linear Contextual Bandits

arXiv 2110.14177 ↗First posted 27 Oct 2021stat.ML cs.IT cs.LGcited by 61

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel federated linear contextual bandits model, where individual clients face different K-armed stochastic bandits coupled through common global parameters. By leveraging the geometric structure of the linear rewards, a collaborative algorithm called Fed-PE is proposed to cope with the heterogeneity across clients without exchanging local feature vectors or raw data. Fed-PE relies on a novel multi-client G-optimal design, and achieves near-optimal regrets for both disjoint and shared parameter cases with logarithmic communication costs. In addition, a new concept called collinearly-dependent policies is introduced, based on which a tight minimax regret lower bound for the disjoint parameter case is derived. Experiments demonstrate the effectiveness of the proposed algorithms on both synthetic and real-world datasets.

Key facts. Cited by 61 papers in the map (data through 14 Oct 2026). Builds on 23 of its 64 references that are in the map. First posted on arXiv 27 Oct 2021.

Builds on

23 of 64 references.

References · 23

  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. 2021Convex optimizationcited by 2,515
  4. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  5. 2014Online Clustering of Banditscited by 102
  6. 2019Batched Multi-armed Bandits Problemcited by 98
  7. 2020Differentially-Private Federated Linear Banditscited by 83
  8. 2020Stochastic Linear Bandits Robust to Adversarial Attackscited by 65
  9. 2020Sequential Batch Learning in Finite-Action Linear Contextual Banditscited by 63
  10. 2021Federated Multi-armed Bandits with Personalizationcited by 62
  11. 2021Federated Multi-Armed Banditscited by 59
  12. 2020Federated Bandit: A Gossiping Approachcited by 55
11 more
  1. 2016Distributed Clustering of Linear Bandits in Peer to Peer Networkscited by 50
  2. 2013A Gang of Banditscited by 49
  3. 2018SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Banditscited by 47
  4. 2016On Context-Dependent Clustering of Banditscited by 44
  5. 2015On Distributed Cooperative Decision-Making in Multiarmed Banditscited by 33
  6. 2020Federated Recommendation System via Differential Privacycited by 26
  7. 2020Decentralized Multi-player Multi-armed Bandits with No Collision Informationcited by 25
  8. 2014Concurrent bandits and cognitive radio networkscited by 24
  9. 2017Estimation Considerations in Contextual Banditscited by 23
  10. 2020Federated Residual Learningcited by 23
  11. 2018The Externalities of Exploration and How Data Diversity Helps Exploitationcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 20; 2023: 20; 2024: 12; 2025: 7; 2026: 1.

61 papers.

Sort:

By area:

  1. 2022A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Banditscited by 28
  2. 2022Near-Optimal Collaborative Learning in Banditscited by 18
  3. 2022Federated Neural Banditscited by 17
  4. 2022Communication Efficient Distributed Learning for Kernelized Contextual Banditscited by 15
  5. 2023On Differentially Private Federated Linear Contextual Banditscited by 14
  6. 2021Collaborative Pure Exploration in Kernel Banditcited by 13
  7. 2022Communication Efficient Federated Learning for Generalized Linear Banditscited by 13
  8. 2022Distributed Contextual Linear Bandits with Minimax Optimal Communication Costcited by 13
  9. 2023Federated Linear Contextual Bandits with User-level Differential Privacycited by 12
  10. 2023Online Clustering of Bandits with Misspecified User Modelscited by 12
  11. 2023Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewardscited by 11
  12. 2022Linear Stochastic Bandits over a Bit-Constrained Channelcited by 9
38 more
  1. 2022Byzantine-Robust Federated Linear Banditscited by 8
  2. 2022Differentially Private Linear Bandits with Partial Distributed Feedbackcited by 8
  3. 2022Distributed Linear Bandits under Communication Constraintscited by 8
  4. 2023LLMs-augmented Contextual Banditcited by 8
  5. 2025A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM Responsescited by 8
  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. 2023Pure Exploration in Asynchronous Federated Banditscited by 6
  11. 2024On the Necessity of Collaboration for Online Model Selection with Decentralized Datacited by 6
  12. 2024FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clientscited by 6
  13. 2022Federated X-Armed Banditcited by 5
  14. 2023On the Effect of Defections in Federated Learning and How to Prevent Themcited by 5
  15. 2022Lifelong Bandit Optimization: No Prior and No Regretcited by 4
  16. 2024Federated Linear Contextual Bandits with Heterogeneous Clientscited by 4
  17. 2022Federated Online Sparse Decision Makingcited by 3
  18. 2022Differentially Private Federated Combinatorial Bandits with Constraintscited by 3
  19. 2023Communication-Efficient Collaborative Regret Minimization in Multi-Armed Banditscited by 3
  20. 2023Incentivized Communication for Federated Banditscited by 3
  21. 2023Federated Linear Bandits with Finite Adversarial Actionscited by 3
  22. 2022One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learningcited by 2
  23. 2022Distributed Stochastic Bandit Learning with Delayed Context Observationcited by 2
  24. 2023An Empirical Evaluation of Federated Contextual Bandit Algorithmscited by 2
  25. 2024Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraintscited by 2
  26. 2024Incentivized Truthful Communication for Federated Banditscited by 2
  27. 2025Federated Linear Dueling Banditscited by 2
  28. 2025Heterogeneous Multi-agent Multi-armed Bandits on Stochastic Block Modelscited by 2
  29. 2022Settling the Communication Complexity for Distributed Offline Reinforcement Learningcited by 1
  30. 2023Federated Learning for Heterogeneous Bandits with Unobserved Contextscited by 1
  31. 2023Regret Lower Bounds in Multi-agent Multi-armed Banditcited by 1
  32. 2023Harnessing the Power of Federated Learning in Federated Contextual Banditscited by 1
  33. 2024Decentralized Blockchain-based Robust Multi-agent Multi-armed Banditcited by 1
  34. 2024Personalized Federated Learning Techniques: Empirical Analysiscited by 1
  35. 2024Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-upscited by 1
  36. 2024Comparative Performance of Collaborative Bandit Algorithms: Effect of Sparsity and Exploration Intensitycited by 1
  37. 2026Batched Stochastic Linear Bandits with 1-Bit Communication Constraintscited by 1
  38. 2022Vertical Federated Linear Contextual Banditscited by 0

50 most cited of 61 All 61 (JSON)