mlsanityData to 7 Oct 2026

Incentivized Collaboration in Active Learning

arXiv 2311.00260 ↗First posted 1 Nov 2023cs.GT cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In collaborative active learning, where multiple agents try to learn labels from a common hypothesis, we introduce an innovative framework for incentivized collaboration. Here, rational agents aim to obtain labels for their data sets while keeping label complexity at a minimum. We focus on designing (strict) individually rational (IR) collaboration protocols, ensuring that agents cannot reduce their expected label complexity by acting individually. We first show that given any optimal active learning algorithm, the collaboration protocol that runs the algorithm as is over the entire data is already IR. However, computing the optimal algorithm is NP-hard. We therefore provide collaboration protocols that achieve (strict) IR and are comparable with the best known tractable approximation algorithm in terms of label complexity.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 54 references that are in the map. First posted on arXiv 1 Nov 2023.

Builds on

31 of 54 references.

References · 31

  1. 2019Introduction to Multi-Armed Banditscited by 475
  2. 2015Strategic Classificationcited by 256
  3. 2020Collaborative Fairness in Federated Learningcited by 95
  4. 2020Model-sharing Games: Analyzing Federated Learning Under Voluntary Participationcited by 60
  5. 2015Bayesian Incentive-Compatible Bandit Explorationcited by 53
  6. 2022Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairnesscited by 45
  7. 2021Optimality and Stability in Federated Learning: A Game-theoretic Approachcited by 40
  8. 2021One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learningcited by 39
  9. 2016Bayesian Exploration: Incentivizing Exploration in Bayesian Gamescited by 37
  10. 2019Advancing subgroup fairness via sleeping expertscited by 28
  11. 2020The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexitycited by 26
  12. 2018Incentivizing Exploration with Selective Data Disclosurecited by 24
19 more
  1. 2021Fair Exploration via Axiomatic Bargainingcited by 21
  2. 2022Active Learning with Safety Constraintscited by 16
  3. 2019Bayesian Exploration with Heterogeneous Agentscited by 12
  4. 2017Competing Bandits: Learning under Competitioncited by 9
  5. 2021Models of fairness in federated learningcited by 8
  6. 2023Learning with Exposure Constraints in Recommendation Systemscited by 8
  7. 2023Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learningcited by 8
  8. 2019Fiduciary Banditscited by 7
  9. 2018Optimal Algorithm for Bayesian Incentive-Compatible Explorationcited by 6
  10. 2020Combining Federated and Active Learning for Communication-efficient Distributed Failure Prediction in Aeronauticscited by 6
  11. 2022Efficient Algorithms for Planning with Participation Constraintscited by 6
  12. 2023Bandit Social Learning: Exploration under Myopic Behaviorcited by 6
  13. 2021Incentive-Compatible Kidney Exchange in a Slightly Semi-Random Modelcited by 4
  14. 2023Incentivized Communication for Federated Banditscited by 3
  15. 2014Active Learning and Best-Response Dynamicscited by 2
  16. 2019Incentive Compatible Active Learningcited by 2
  17. 2023A Framework for Incentivized Collaborative Learningcited by 2
  18. 2016Opting Into Optimal Matchingscited by 1
  19. 2020Kidney exchange and endless paths: On the optimal use of an altruistic donorcited by 1

Built on by

Not cited yet.