Long-Term Fairness in Sequential Multi-Agent Selection with Positive Reinforcement

• URL: http://arxiv.org/abs/2407.07350v1
• Date: Wed, 10 Jul 2024 04:03:23 GMT
• Title: Long-Term Fairness in Sequential Multi-Agent Selection with Positive Reinforcement
• Authors: Bhagyashree Puranik, Ozgur Guldogan, Upamanyu Madhow, Ramtin Pedarsani,
• Abstract summary: In selection processes such as college admissions or hiring, biasing slightly towards applicants from under-represented groups is hypothesized to provide positive feedback. We propose the Multi-agent Fair-Greedy policy, which balances greedy score and fairness. Our results indicate that, while positive reinforcement is a promising mechanism for long-term fairness, policies must be designed carefully to be robust to variations in the evolution model.
• Score: 21.44063458579184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While much of the rapidly growing literature on fair decision-making focuses on metrics for one-shot decisions, recent work has raised the intriguing possibility of designing sequential decision-making to positively impact long-term social fairness. In selection processes such as college admissions or hiring, biasing slightly towards applicants from under-represented groups is hypothesized to provide positive feedback that increases the pool of under-represented applicants in future selection rounds, thus enhancing fairness in the long term. In this paper, we examine this hypothesis and its consequences in a setting in which multiple agents are selecting from a common pool of applicants. We propose the Multi-agent Fair-Greedy policy, that balances greedy score maximization and fairness. Under this policy, we prove that the resource pool and the admissions converge to a long-term fairness target set by the agents when the score distributions across the groups in the population are identical. We provide empirical evidence of existence of equilibria under non-identical score distributions through synthetic and adapted real-world datasets. We then sound a cautionary note for more complex applicant pool evolution models, under which uncoordinated behavior by the agents can cause negative reinforcement, leading to a reduction in the fraction of under-represented applicants. Our results indicate that, while positive reinforcement is a promising mechanism for long-term fairness, policies must be designed carefully to be robust to variations in the evolution model, with a number of open issues that remain to be explored by algorithm designers, social scientists, and policymakers.

Related papers

• Average-Case Analysis of Iterative Voting [33.68929251752289]
  Iterative voting is a natural model of repeated strategic decision-making in social choice. Prior work has analyzed the efficacy of iterative plurality on the welfare of the chosen outcome at equilibrium. This work extends average-case analysis to a wider class of distributions and distinguishes when iterative plurality improves or degrades welfare.
  arXiv  Detail & Related papers  (2024-02-13T00:46:46Z)
• Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity [15.78130132380848]
  Algorithmic recourse has gained attention as a means of giving persons agency in their interactions with AI systems. Recent work has shown that recourse itself may be unfair due to differences in the initial circumstances of individuals. Time is a critical element in recourse because the longer it takes an individual to act, the more the setting may change.
  arXiv  Detail & Related papers  (2024-01-29T11:55:45Z)
• Pure Exploration under Mediators' Feedback [63.56002444692792]
  Multi-armed bandits are a sequential-decision-making framework, where, at each interaction step, the learner selects an arm and observes a reward. We consider the scenario in which the learner has access to a set of mediators, each of which selects the arms on the agent's behalf according to a and possibly unknown policy. We propose a sequential decision-making strategy for discovering the best arm under the assumption that the mediators' policies are known to the learner.
  arXiv  Detail & Related papers  (2023-08-29T18:18:21Z)
• Estimating and Incentivizing Imperfect-Knowledge Agents with Hidden Rewards [4.742123770879715]
  In practice, incentive providers often cannot observe the reward realizations of incentivized agents. This paper explores a repeated adverse selection game between a self-interested learning agent and a learning principal. We introduce an estimator whose only input is the history of principal's incentives and agent's choices.
  arXiv  Detail & Related papers  (2023-08-13T08:12:01Z)
• Moral Machine or Tyranny of the Majority? [25.342029326793917]
  In Moral Machine project, researchers crowdsourced answers to "Trolley Problems" concerning autonomous vehicles. Noothigattu et al. proposed inferring linear functions that approximate each individual's preferences and aggregating these linear models by averaging parameters across the population. In this paper, we examine this averaging mechanism, focusing on fairness concerns in the presence of strategic effects.
  arXiv  Detail & Related papers  (2023-05-27T00:49:11Z)
• Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective [50.093280002375984]
  Performance unfairness among variables widely exists in multivariate time series (MTS) forecasting models. We propose a novel framework, named FairFor, for fairness-aware MTS forecasting.
  arXiv  Detail & Related papers  (2023-01-27T04:54:12Z)
• Social Diversity Reduces the Complexity and Cost of Fostering Fairness [63.70639083665108]
  We investigate the effects of interference mechanisms which assume incomplete information and flexible standards of fairness. We quantify the role of diversity and show how it reduces the need for information gathering. Our results indicate that diversity changes and opens up novel mechanisms available to institutions wishing to promote fairness.
  arXiv  Detail & Related papers  (2022-11-18T21:58:35Z)
• Long-term dynamics of fairness: understanding the impact of data-driven targeted help on job seekers [1.357291726431012]
  We use an approach that combines statistics and machine learning to assess long-term fairness effects of labor market interventions. We develop and use a model to investigate the impact of decisions caused by a public employment authority that selectively supports job-seekers. We conclude that in order to quantify the trade-off correctly and to assess the long-term fairness effects of such a system in the real-world, careful modeling of the surrounding labor market is indispensable.
  arXiv  Detail & Related papers  (2022-08-17T12:03:23Z)
• Statistical discrimination in learning agents [64.78141757063142]
  Statistical discrimination emerges in agent policies as a function of both the bias in the training population and of agent architecture. We show that less discrimination emerges with agents that use recurrent neural networks, and when their training environment has less bias.
  arXiv  Detail & Related papers  (2021-10-21T18:28:57Z)
• Addressing the Long-term Impact of ML Decisions via Policy Regret [49.92903850297013]
  We study a setting in which the reward from each arm evolves every time the decision-maker pulls that arm. We argue that an acceptable sequential allocation of opportunities must take an arm's potential for growth into account. We present an algorithm with provably sub-linear policy regret for sufficiently long time horizons.
  arXiv  Detail & Related papers  (2021-06-02T17:38:10Z)
• Multi-Stage Decentralized Matching Markets: Uncertain Preferences and Strategic Behaviors [91.3755431537592]
  This article develops a framework for learning optimal strategies in real-world matching markets. We show that there exists a welfare-versus-fairness trade-off that is characterized by the uncertainty level of acceptance. We prove that participants can be better off with multi-stage matching compared to single-stage matching.
  arXiv  Detail & Related papers  (2021-02-13T19:25:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.