paper-with-me

Papers

Auditing and Achieving Intersectional Fairness in Classification Problems

2019-11-04 · Giulio Morina, Viktoriia Oliinyk, Julian Waton, Ines Marusic, Konstantinos Georgatzis

Machine learning algorithms are extensively used to make increasingly more consequential decisions about people, so achieving optimal predictive performance can no longer be the only focus. A particularly important consideration is fairness with respect to race, gender, or any other sensitive attribute. This paper studies intersectional fairness, where intersections of multiple sensitive attributes are considered. Prior research has mainly focused on fairness with respect to a single sensitive attribute, with intersectional fairness being comparatively less studied despite its critical importance for the safety of modern machine learning systems. We present a comprehensive framework for auditing and achieving intersectional fairness in classification problems: we define a suite of metrics to assess intersectional fairness in the data or model outputs by extending known single-attribute fairness metrics, and propose methods for robustly estimating them even when some intersectional subgroups are underrepresented. Furthermore, we develop post-processing techniques to mitigate any detected intersectional bias in a classification model. Our techniques do not rely on any assumptions regarding the underlying model and preserve predictive performance at a guaranteed level of fairness. Finally, we give guidance on a practical implementation, showing how the proposed methods perform on a real-world dataset.

📄 PDF Abstract BibTeX arXiv:1911.01468

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeBIG-bench Machine LearningClassificationFairnessGeneral Classification

Similar Papers 제목 키워드 기반

Auditing Predictive Models for Intersectional Biases

2023-06-22 · Kate S. Boxer, Edward McFowland III, Daniel B. Neill

Predictive models that satisfy group fairness criteria in aggregate for members of a protected class, but do not guarantee subgroup fairness, could produce biased predictions for individuals at the intersection of two or…

Bias DetectionFairness

Evaluating Intersectional Fairness across Clinical Machine Learning Use Cases using Fairlogue and the All of Us Research Program

2026-04-07 · Nick Souligne, Vignesh Subbian arxiv

Intersectional biases in healthcare data can produce compound disparities in clinical machine learning models, yet most fairness evaluations assess demographic attributes independently. FairLogue, a toolkit for intersect…

The Intersectionality Problem for Algorithmic Fairness

2024-11-04 · Johannes Himmelreich, Arbie Hsu, Kristian Lum, Ellen Veomett

A yet unmet challenge in algorithmic fairness is the problem of intersectionality, that is, achieving fairness across the intersection of multiple groups -- and verifying that such fairness has been attained. Because int…

Fairness

One-vs.-One Mitigation of Intersectional Bias: A General Method to Extend Fairness-Aware Binary Classification

2020-10-26 · Kenji Kobayashi, Yuri Nakao

With the widespread adoption of machine learning in the real world, the impact of the discriminatory bias has attracted attention. In recent years, various methods to mitigate the bias have been proposed. However, most o…

BIG-bench Machine LearningBinary ClassificationClassificationFairness+1

Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure

2024-05-23 · Gaurav Maheshwari, Aurélien Bellet, Pascal Denis, Mikaela Keller

In this paper, we introduce a data augmentation approach specifically tailored to enhance intersectional fairness in classification tasks. Our method capitalizes on the hierarchical structure inherent to intersectionalit…

Data AugmentationFairnessSynthetic Data Generation