# Incentivized Collaboration in Active Learning

arXiv: https://arxiv.org/abs/2311.00260 · HTML: https://mlsanity.com/paper/2311.00260/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 54 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Builds on (most cited first, 30 of 31)

- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [Strategic Classification](https://mlsanity.com/paper/1506.06980/) (2015)
- [Collaborative Fairness in Federated Learning](https://mlsanity.com/paper/2008.12161/) (2020)
- [Model-sharing Games: Analyzing Federated Learning Under Voluntary Participation](https://mlsanity.com/paper/2010.00753/) (2020)
- [Bayesian Incentive-Compatible Bandit Exploration](https://mlsanity.com/paper/1502.04147/) (2015)
- [Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairness](https://mlsanity.com/paper/2202.08821/) (2022)
- [Optimality and Stability in Federated Learning: A Game-theoretic Approach](https://mlsanity.com/paper/2106.09580/) (2021)
- [One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning](https://mlsanity.com/paper/2103.03228/) (2021)
- [Bayesian Exploration: Incentivizing Exploration in Bayesian Games](https://mlsanity.com/paper/1602.07570/) (2016)
- [Advancing subgroup fairness via sleeping experts](https://mlsanity.com/paper/1909.08375/) (2019)
- [The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity](https://mlsanity.com/paper/2002.00558/) (2020)
- [Incentivizing Exploration with Selective Data Disclosure](https://mlsanity.com/paper/1811.06026/) (2018)
- [Fair Exploration via Axiomatic Bargaining](https://mlsanity.com/paper/2106.02553/) (2021)
- [Active Learning with Safety Constraints](https://mlsanity.com/paper/2206.11183/) (2022)
- [Bayesian Exploration with Heterogeneous Agents](https://mlsanity.com/paper/1902.07119/) (2019)
- [Competing Bandits: Learning under Competition](https://mlsanity.com/paper/1702.08533/) (2017)
- [Models of fairness in federated learning](https://mlsanity.com/paper/2112.00818/) (2021)
- [Learning with Exposure Constraints in Recommendation Systems](https://mlsanity.com/paper/2302.01377/) (2023)
- [Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learning](https://mlsanity.com/paper/2306.05592/) (2023)
- [Fiduciary Bandits](https://mlsanity.com/paper/1905.07043/) (2019)
- [Optimal Algorithm for Bayesian Incentive-Compatible Exploration](https://mlsanity.com/paper/1810.10304/) (2018)
- [Combining Federated and Active Learning for Communication-efficient Distributed Failure Prediction in Aeronautics](https://mlsanity.com/paper/2001.07504/) (2020)
- [Efficient Algorithms for Planning with Participation Constraints](https://mlsanity.com/paper/2205.07767/) (2022)
- [Bandit Social Learning: Exploration under Myopic Behavior](https://mlsanity.com/paper/2302.07425/) (2023)
- [Incentive-Compatible Kidney Exchange in a Slightly Semi-Random Model](https://mlsanity.com/paper/2106.11387/) (2021)
- [Incentivized Communication for Federated Bandits](https://mlsanity.com/paper/2309.11702/) (2023)
- [Active Learning and Best-Response Dynamics](https://mlsanity.com/paper/1406.6633/) (2014)
- [Incentive Compatible Active Learning](https://mlsanity.com/paper/1911.05171/) (2019)
- [A Framework for Incentivized Collaborative Learning](https://mlsanity.com/paper/2305.17052/) (2023)
- [Opting Into Optimal Matchings](https://mlsanity.com/paper/1609.04051/) (2016)

## 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.