Fairness through awareness
- 8 January 2012
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 214-226
- https://doi.org/10.1145/2090236.2090255
Abstract
We study fairness in classification, where individuals are classified, e.g., admitted to a university, and the goal is to prevent discrimination against individuals based on their membership in some group, while maintaining utility for the classifier (the university). The main conceptual contribution of this paper is a framework for fair classification comprising (1) a (hypothetical) task-specific metric for determining the degree to which individuals are similar with respect to the classification task at hand; (2) an algorithm for maximizing utility subject to the fairness constraint, that similar individuals are treated similarly. We also present an adaptation of our approach to achieve the complementary goal of "fair affirmative action," which guarantees statistical parity (i.e., the demographics of the set of individuals receiving any classification are the same as the demographics of the underlying population), while treating similar individuals as similarly as possible. Finally, we discuss the relationship of fairness to privacy: when fairness implies privacy, and how tools developed in the context of differential privacy may be applied to fairness.Keywords
Other Versions
This publication has 10 references indexed in Scilit:
- Mechanism design with uncertain inputsPublished by Association for Computing Machinery (ACM) ,2011
- On the geometry of differential privacyPublished by Association for Computing Machinery (ACM) ,2010
- Towards Sharp Inapproximability For Any 2-CSPPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- The Santa Claus problemPublished by Association for Computing Machinery (ACM) ,2006
- Differential PrivacyLecture Notes in Computer Science, 2006
- Calibrating Noise to Sensitivity in Private Data AnalysisLecture Notes in Computer Science, 2006
- Metric Embeddings with Relaxed GuaranteesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A Linear Programming Formulation and Approximation Algorithms for the Metric Labeling ProblemSIAM Journal on Discrete Mathematics, 2004
- Approximation algorithms for classification problems with pairwise relationshipsJournal of the ACM, 2002
- Fairness in SchedulingJournal of Algorithms, 1998