mlsanityData to 14 Oct 2026

Learning with Limited Shared Information in Multi-agent Multi-armed Bandit

arXiv 2502.15338 ↗First posted 21 Feb 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-agent multi-armed bandit (MAMAB) is a classic collaborative learning model and has gained much attention in recent years. However, existing studies do not consider the case where an agent may refuse to share all her information with others, e.g., when some of the data contains personal privacy. In this paper, we propose a novel limited shared information multi-agent multi-armed bandit (LSI-MAMAB) model in which each agent only shares the information that she is willing to share, and propose the Balanced-ETC algorithm to help multiple agents collaborate efficiently with limited shared information. Our analysis shows that Balanced-ETC is asymptotically optimal and its average regret (on each agent) approaches a constant when there are sufficient agents involved. Moreover, to encourage agents to participate in this collaborative learning, an incentive mechanism is proposed to make sure each agent can benefit from the collaboration system. Finally, we present experimental results to validate our theoretical results.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 44 references that are in the map. First posted on arXiv 21 Feb 2025.

Builds on

22 of 44 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  3. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  4. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 243
  5. 2021Federated Multi-armed Bandits with Personalizationcited by 62
  6. 2021Federated Multi-Armed Banditscited by 59
  7. 2015Bayesian Incentive-Compatible Bandit Explorationcited by 53
  8. 2019Social Learning in Multi Agent Multi Armed Banditscited by 48
  9. 2019Energy Demand Prediction with Federated Learning for Electric Vehicle Networkscited by 46
  10. 2021A Comprehensive Survey of Incentive Mechanism for Federated Learningcited by 38
  11. 2016Bayesian Exploration: Incentivizing Exploration in Bayesian Gamescited by 37
  12. 2018Efficient Decentralized Deep Learning by Dynamic Model Averagingcited by 30
10 more
  1. 2021Multi-Agent Multi-Armed Bandits with Limited Communicationcited by 29
  2. 2018Incentivizing Exploration with Selective Data Disclosurecited by 24
  3. 2021Fair Exploration via Axiomatic Bargainingcited by 22
  4. 2020Robust Multi-Agent Multi-Armed Banditscited by 20
  5. 2023Player-optimal Stable Regret for Bandit Learning in Matching Marketscited by 17
  6. 2018Multi-armed Bandits with Compensationcited by 13
  7. 2021When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Banditscited by 8
  8. 2015Incentivizing Exploration with Heterogeneous Value of Moneycited by 6
  9. 2021Incentivizing Exploration in Linear Bandits under Information Gapcited by 5
  10. 2020Bayesian Persuasion under Ex Ante and Ex Post Constraintscited by 2

Built on by

Not cited yet.