Long-Term Fairness with Unknown Dynamics
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement LearningFairnessreinforcement-learningReinforcement LearningSimilar Papers 제목 키워드 기반
Causal Modeling for Fairness in Dynamical Systems
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 …
FairnessTier Balancing: Towards Dynamic Fairness over Underlying Causal Factors
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 MakingFairnessHow Do Fair Decisions Fare in Long-term Qualification?
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 MakingFairnessLong-term Fairness with Selective Labels
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 LearningWhat Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning
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