Shapley meets Rawls: an integrated framework for measuring and explaining unfairness
Explainability and fairness have mainly been considered separately, with recent exceptions trying the explain the sources of unfairness. This paper shows that the Shapley value can be used to both define and explain unfairness, under standard group fairness criteria. This offers an integrated framework to estimate and derive inference on unfairness as-well-as the features that contribute to it. Our framework can also be extended from Shapley values to the family of Efficient-Symmetric-Linear (ESL) values, some of which offer more robust definitions of fairness, and shorter computation times. An illustration is run on the Census Income dataset from the UCI Machine Learning Repository. Our approach shows that `Age", Number of hours" and `Marital status" generate gender unfairness, using shorter computation time than traditional Bootstrap tests.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Absolute Shapley Value
Shapley value is a concept in cooperative game theory for measuring the contribution of each participant, which was named in honor of Lloyd Shapley. Shapley value has been recently applied in data marketplaces for compen…
FairnessGeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Models
This paper introduces GeoShapley, a game theory approach to measuring spatial effects in machine learning models. GeoShapley extends the Nobel Prize-winning Shapley value framework in game theory by conceptualizing locat…
Additive modelsMeasuring Participant Contributions in Decentralized Federated Learning
Federated learning (FL) enables multiple clients to collaboratively train models without sharing their data. Measuring participant contributions in FL is crucial for incentivizing clients and ensuring transparency. While…
Federated LearningOn the Convergence of the Shapley Value in Parametric Bayesian Learning Games
Measuring contributions is a classical problem in cooperative game theory where the Shapley value is the most well-known solution concept. In this paper, we establish the convergence property of the Shapley value in para…
Bayesian InferenceFrom Utilitarian to Rawlsian Designs for Algorithmic Fairness
There is a lack of consensus within the literature as to how `fairness' of algorithmic systems can be measured, and different metrics can often be at odds. In this paper, we approach this task by drawing on the ethical f…
Fairness