paper-with-me

Papers

Long-Term Fairness with Unknown Dynamics

2023-04-19 · NeurIPS 2023 11

While machine learning can myopically reinforce social inequalities, it may also be used to dynamically seek equitable outcomes. In this paper, we formalize long-term fairness in the context of online reinforcement learning. This formulation can accommodate dynamical control objectives, such as driving equity inherent in the state of a population, that cannot be incorporated into static formulations of fairness. We demonstrate that this framing allows an algorithm to adapt to unknown dynamics by sacrificing short-term incentives to drive a classifier-population system towards more desirable equilibria. For the proposed setting, we develop an algorithm that adapts recent work in online learning. We prove that this algorithm achieves simultaneous probabilistic bounds on cumulative loss and cumulative violations of fairness (as statistical regularities between demographic groups). We compare our proposed algorithm to the repeated retraining of myopic classifiers, as a baseline, and to a deep reinforcement learning algorithm that lacks safety guarantees. Our experiments model human populations according to evolutionary game theory and integrate real-world datasets.

📄 PDF Abstract BibTeX arXiv:2304.09362

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningFairnessreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Causal Modeling for Fairness in Dynamical Systems

2019-09-18 · ICML 2020 1 · Elliot Creager, David Madras, Toniann Pitassi, Richard Zemel

In many application areas---lending, education, and online recommenders, for example---fairness and equity concerns emerge when a machine learning system interacts with a dynamically changing environment to produce both …

Fairness

Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors

2023-01-21 · Zeyu Tang, Yatong Chen, Yang Liu, Kun Zhang

The pursuit of long-term fairness involves the interplay between decision-making and the underlying data generating process. In this paper, through causal modeling with a directed acyclic graph (DAG) on the decision-dist…

Decision MakingFairness

How Do Fair Decisions Fare in Long-term Qualification?

2020-10-21 · NeurIPS 2020 12 · Xueru Zhang, Ruibo Tu, Yang Liu, Mingyan Liu 외

Although many fairness criteria have been proposed for decision making, their long-term impact on the well-being of a population remains unclear. In this work, we study the dynamics of population qualification and algori…

Decision MakingFairness

Long-term Fairness with Selective Labels

2026-05-21 · Giovani Valdrighi, Isabel Valera, Marcos Medeiros Raimundo arxiv

Long-term fairness algorithms aim to satisfy fairness beyond static and short-term notions by accounting for the dynamics between decision-making policies and population behavior. Most previous approaches evaluate perfor…

Reinforcement Learning

What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning

2024-04-16 · Zhihong Deng, Jing Jiang, Guodong Long, Chengqi Zhang

In sequential decision-making problems involving sensitive attributes like race and gender, reinforcement learning (RL) agents must carefully consider long-term fairness while maximizing returns. Recent works have propos…

AttributecounterfactualDecision MakingFairness+4