Harnessing the Power of Federated Learning in Federated Contextual Bandits
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) has demonstrated great potential in revolutionizing distributed machine learning, and tremendous efforts have been made to extend it beyond the original focus on supervised learning. Among many directions, federated contextual bandits (FCB), a pivotal integration of FL and sequential decision-making, has garnered significant attention in recent years. Despite substantial progress, existing FCB approaches have largely employed their tailored FL components, often deviating from the canonical FL framework. Consequently, even renowned algorithms like FedAvg remain under-utilized in FCB, let alone other FL advancements. Motivated by this disconnection, this work takes one step towards building a tighter relationship between the canonical FL study and the investigations on FCB. In particular, a novel FCB design, termed FedIGW, is proposed to leverage a regression-based CB algorithm, i.e., inverse gap weighting. Compared with existing FCB approaches, the proposed FedIGW design can better harness the entire spectrum of FL innovations, which is concretely reflected as (1) flexible incorporation of (both existing and forthcoming) FL protocols; (2) modularized plug-in of FL analyses in performance guarantees; (3) seamless integration of FL appendages (such as personalization, robustness, and privacy). We substantiate these claims through rigorous theoretical analyses and empirical evaluations.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 72 of its 105 references that are in the map. First posted on arXiv 26 Dec 2023.
Builds on
72 of 105 references.
References · 72
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
- 2020Adaptive Federated Optimizationcited by 1,036
- 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
- 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
- 2019Agnostic Federated Learningcited by 451
- 2019Robust Aggregation for Federated Learningcited by 314
- 2020Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oraclescited by 195
38 more
- 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
- 2020Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizabilitycited by 114
- 2021Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approachcited by 98
- 2021Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learningcited by 93
- 2020Federated Unsupervised Representation Learningcited by 92
- 2020Fairness-aware Agnostic Federated Learningcited by 87
- 2020Differentially-Private Federated Linear Banditscited by 83
- 2020Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspectivecited by 78
- 2022Divergence-aware Federated Self-Supervised Learningcited by 71
- 2020Sequential Batch Learning in Finite-Action Linear Contextual Banditscited by 63
- 2021Federated Multi-armed Bandits with Personalizationcited by 62
- 2021Federated Linear Contextual Banditscited by 61
- 2022Federated Reinforcement Learning with Environment Heterogeneitycited by 61
- 2021Federated Multi-Armed Banditscited by 59
- 2020Federated Bandit: A Gossiping Approachcited by 55
- 2021Fault-Tolerant Federated Reinforcement Learning with Theoretical Guaranteecited by 52
- 2020Design and Analysis of Uplink and Downlink Communications for Federated Learningcited by 48
- 2013Distributed Exploration in Multi-Armed Banditscited by 46
- 2018SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Banditscited by 46
- 2022Orchestra: Unsupervised Federated Learning via Globally Consistent Clusteringcited by 45
- 2020Efficient and Robust Algorithms for Adversarial Linear Contextual Banditscited by 42
- 2019Attack-Resistant Federated Learning with Residual-based Reweightingcited by 40
- 2020Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Banditscited by 35
- 2021Personalized Federated Learning: A Unified Framework and Universal Optimization Techniquescited by 34
- 2015On Distributed Cooperative Decision-Making in Multiarmed Banditscited by 33
- 2019Variance-Reduced Decentralized Stochastic Optimization with Accelerated Convergencecited by 33
- 2022Contextual Bandits with Large Action Spaces: Made Practicalcited by 32
- 2021Asynchronous Upper Confidence Bound Algorithms for Federated Linear Banditscited by 31
- 2018COLA: Decentralized Linear Learningcited by 30
- 2022Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescited by 30
- 2022A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Banditscited by 28
- 2020Decentralized Multi-player Multi-armed Bandits with No Collision Informationcited by 25
- 2022Privacy-Preserving Aggregation in Federated Learning: A Surveycited by 25
- 2020Federated Residual Learningcited by 23
- 2021Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximationcited by 23
- 2021Adapting to Misspecification in Contextual Bandits with Offline Regression Oraclescited by 21
- 2021Parallelizing Thompson Samplingcited by 20
- 2021Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalizationcited by 18
50 most cited of 72 All 72 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.