May 13, 2021 · In our paper, we present a method of expanding fairness metrics to measure intersectional fairness, which we call the Worst-Case Disparity Framework.
Missing: Capture | Show results with:Capture
People also ask
What is intersectional fairness?
How to demonstrate intersectionality?
How to ensure data fairness?
How to fight intersectionality?
May 21, 2023 · First, we illustrate various shortcomings of existing fairness measures commonly used to capture intersectional fairness. Then, we propose a new ...
Dec 6, 2023 · To capture these effects in the context of machine learning, several intersectional fairness measures have been proposed (Kearns et al., 2018; ...
Feb 7, 2025 · We offer a description of the main ways to incorporate intersectionality in fair ranking systems through practical examples and provide a comparative overview ...
Missing: Capture | Show results with:Capture
We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality.
Jun 1, 2022 · An intersectional approach allows you to identify which people, groups, or subgroups are experiencing unfair outcomes, and to see that within ...
Missing: Capture | Show results with:Capture
First, we illustrate various shortcomings of existing fairness measures commonly used to capture intersectional fairness. Then, we propose a new framework ...
Feb 27, 2023 · This academic paper proposes a fractal approach to intersectional fairness in AI and suggests that fairness requires a bottom-up approach.
First, we illustrate various shortcomings of existing fairness measures commonly used to capture intersectional fairness. Then, we propose a new framework ...
Probabilistic fairness captures the expected size δ of the population for which the predictor discriminates more than ϵ. 2.7 Discussions. In contrast to ...