An Intersectional Definition of Fairness
Machine Learning
2019-09-11 v3 Computers and Society
Machine Learning
Abstract
We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens arising from the Humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including gender, race, sexual orientation, class, and disability. We show that our criteria behave sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. We provide a learning algorithm which respects our intersectional fairness criteria. Case studies on census data and the COMPAS criminal recidivism dataset demonstrate the utility of our methods.
Cite
@article{arxiv.1807.08362,
title = {An Intersectional Definition of Fairness},
author = {James Foulds and Rashidul Islam and Kamrun Naher Keya and Shimei Pan},
journal= {arXiv preprint arXiv:1807.08362},
year = {2019}
}