Wasserstein-based fairness interpretability framework for machine learning models
The objective of this article is to introduce a fairness interpretability framework for measuring and explaining the bias in classification and regression models at the level of a distribution. In our work, we measure the model bias across sub-population distributions in the model output using the Wasserstein metric. To properly quantify the contributions of predictors, we take into account the favorability of both the model and predictors with respect to the non-protected class. The quantification is accomplished by the use of transport theory, which gives rise to the decomposition of the model bias and bias explanations to positive and negative contributions. To gain more insight into the role of favorability and allow for additivity of bias explanations, we adapt techniques from cooperative game theory.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningFairnessregressionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Model-agnostic bias mitigation methods with regressor distribution control for Wasserstein-based fairness metrics
This article is a companion paper to our earlier work Miroshnikov et al. (2021) on fairness interpretability, which introduces bias explanations. In the current work, we propose a bias mitigation methodology based upon t…
Bayesian OptimizationFairnessGeometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings
Fairness-accuracy trade-offs are a central concern in the deployment of fairness-aware machine learning methods. When sensitive attributes are unavailable at inference time-the so called unawareness setting, principled m…
Fairness with Wasserstein Adversarial Networks
Quantifying, enforcing and implementing fairness emerged as a major topic in machine learning. We investigate these questions in the context of deep learning. Our main algorithmic and theoretical tool is the computationa…
FairnessFrom Fragile to Certified: Wasserstein Audits of Group Fairness Under Distribution Shift
Group-fairness metrics (e.g., equalized odds) can vary sharply across resamples and are especially brittle under distribution shift, undermining reliable audits. We propose a Wasserstein distributionally robust framework…
Wasserstein projection distance for fairness testing of regression models
Fairness testing evaluates whether a model satisfies a specified fairness criterion across different groups, yet most research has focused on classification models, leaving regression models underexplored. This paper int…