Consistent End-to-End Estimation for Counterfactual Fairness

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ma, Yuchen, Melnychuk, Valentyn, Frauen, Dennis, Feuerriegel, Stefan
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908572234809344
author Ma, Yuchen
Melnychuk, Valentyn
Frauen, Dennis
Feuerriegel, Stefan
author_facet Ma, Yuchen
Melnychuk, Valentyn
Frauen, Dennis
Feuerriegel, Stefan
contents Fairness in predictions is of direct importance in practice due to legal, ethical, and societal reasons. This is often accomplished through counterfactual fairness, which ensures that the prediction for an individual is the same as that in a counterfactual world under a different sensitive attribute. However, achieving counterfactual fairness is challenging as counterfactuals are unobservable, and, because of that, existing baselines for counterfactual fairness do not have theoretical guarantees. In this paper, we propose a novel counterfactual fairness predictor for making predictions under counterfactual fairness. Here, we follow the standard counterfactual fairness setting and directly learn the counterfactual distribution of the descendants of the sensitive attribute via tailored neural networks, which we then use to enforce fair predictions through a novel counterfactual mediator regularization. Unique to our work is that we provide theoretical guarantees that our method is effective in ensuring the notion of counterfactual fairness. We further compare the performance across various datasets, where our method achieves state-of-the-art performance.
format Preprint
id arxiv_https___arxiv_org_abs_2310_17687
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Consistent End-to-End Estimation for Counterfactual Fairness
Ma, Yuchen
Melnychuk, Valentyn
Frauen, Dennis
Feuerriegel, Stefan
Machine Learning
Computers and Society
Fairness in predictions is of direct importance in practice due to legal, ethical, and societal reasons. This is often accomplished through counterfactual fairness, which ensures that the prediction for an individual is the same as that in a counterfactual world under a different sensitive attribute. However, achieving counterfactual fairness is challenging as counterfactuals are unobservable, and, because of that, existing baselines for counterfactual fairness do not have theoretical guarantees. In this paper, we propose a novel counterfactual fairness predictor for making predictions under counterfactual fairness. Here, we follow the standard counterfactual fairness setting and directly learn the counterfactual distribution of the descendants of the sensitive attribute via tailored neural networks, which we then use to enforce fair predictions through a novel counterfactual mediator regularization. Unique to our work is that we provide theoretical guarantees that our method is effective in ensuring the notion of counterfactual fairness. We further compare the performance across various datasets, where our method achieves state-of-the-art performance.
title Consistent End-to-End Estimation for Counterfactual Fairness
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2310.17687