Fairness Through Awareness

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.

The authors' own abstract, copied from arxiv.org.

How to cite it

Built from the details listed on this page. Check them against the paper before you submit.

Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2011). Fairness Through Awareness. Preprint, not yet peer-reviewed. https://arxiv.org/abs/1104.3913

Dwork, Cynthia, et al. "Fairness Through Awareness." Preprint, not yet peer-reviewed, 2011, https://arxiv.org/abs/1104.3913.

@article{dwork2011fairness,
  title = {Fairness Through Awareness},
  author = {Cynthia Dwork and Moritz Hardt and Toniann Pitassi and Omer Reingold and Rich Zemel},
  journal = {Preprint, not yet peer-reviewed},
  year = {2011},
  url = {https://arxiv.org/abs/1104.3913},
}

What it is

The founding technical paper on algorithmic fairness: defines fairness as treating similar individuals similarly, and shows why blindness to a protected attribute does not deliver it. Mathematical. Free on arXiv.

Topics