An Intersectional Definition of Fairness

Thumbnail Image

Files

1807.08362.pdf (659.96 KB)

Links to Files

https://arxiv.org/abs/1807.08362

Permanent Link

2018arXiv180708362F
 http://hdl.handle.net/11603/11227

Collections

UMBC Information Systems Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

Date

2018-07

Type of Work

journal articles preprints
Text

Department

Program

Citation of Original Publication

Rights

This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please contact the author.

Subjects

Computer Science - Machine Learning
Computer Science - Computers and Society
Statistics - Machine Learning
measure of fairness
algorithms and data
protected attributes
systems of power
systems of oppression
race
gender
sexual orientation
class
disability

Abstract

We introduce a measure of fairness for algorithms and data with regard to multiple protected attributes. Our proposed definition, differential fairness, is informed by the framework of intersectionality, which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including race, gender, sexual orientation, class, and disability. We show that our criterion behaves sensibly for any subset of the set of protected attributes, and we illustrate links to differential privacy. A case study on census data demonstrates the utility of our approach.