paper-with-me

홈 › Papers

Minimax Group Fairness: Algorithms and Experiments

2020-11-05 · Emily Diana, Wesley Gill, Michael Kearns, Krishnaram Kenthapadi, Aaron Roth

We consider a recently introduced framework in which fairness is measured by worst-case outcomes across groups, rather than by the more standard differences between group outcomes. In this framework we provide provably convergent oracle-efficient learning algorithms (or equivalently, reductions to non-fair learning) for minimax group fairness. Here the goal is that of minimizing the maximum loss across all groups, rather than equalizing group losses. Our algorithms apply to both regression and classification settings and support both overall error and false positive or false negative rates as the fairness measure of interest. They also support relaxations of the fairness constraints, thus permitting study of the tradeoff between overall accuracy and minimax fairness. We compare the experimental behavior and performance of our algorithms across a variety of fairness-sensitive data sets and show empirical cases in which minimax fairness is strictly and strongly preferable to equal outcome notions.

📄 PDF Abstract BibTeX arXiv:2011.03108

Code (1)

amazon-research/minimax-fair pytorch

Tasks

Fairness

Similar Papers 제목 키워드 기반

Lexicographically Fair Learning: Algorithms and Generalization

2021-02-16 · Emily Diana, Wesley Gill, Ira Globus-Harris, Michael Kearns 외

We extend the notion of minimax fairness in supervised learning problems to its natural conclusion: lexicographic minimax fairness (or lexifairness for short). Informally, given a collection of demographic groups of inte…

FairnessGeneralization Bounds

Minimax Demographic Group Fairness in Federated Learning

2022-01-20 · Afroditi Papadaki, Natalia Martinez, Martin Bertran, Guillermo Sapiro 외

Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minimax group fairness in federated learning scenarios where d…

FairnessFederated Learning

Minimax AUC Fairness: Efficient Algorithm with Provable Convergence

2022-08-22 · Zhenhuan Yang, Yan Lok Ko, Kush R. Varshney, Yiming Ying

The use of machine learning models in consequential decision making often exacerbates societal inequity, in particular yielding disparate impact on members of marginalized groups defined by race and gender. The area unde…

Decision MakingFairnessStochastic Optimization

Minimax Optimal Fair Classification with Bounded Demographic Disparity

2024-03-27 · Xianli Zeng, Guang Cheng, Edgar Dobriban

Mitigating the disparate impact of statistical machine learning methods is crucial for ensuring fairness. While extensive research aims to reduce disparity, the effect of using a \emph{finite dataset} -- as opposed to th…

Binary ClassificationClassificationFairness

Minimax Group Fairness in Strategic Classification

2024-10-03 · Emily Diana, Saeed Sharifi-Malvajerdi, Ali Vakilian

In strategic classification, agents manipulate their features, at a cost, to receive a positive classification outcome from the learner's classifier. The goal of the learner in such settings is to learn a classifier that…

ClassificationFairness