Operationalizing Individual Fairness with Pairwise Fair Representations

very large data bases, pp. 506-518, 2019.

Cited by: 5|Bibtex|Views48|DOI:https://doi.org/10.14778/3372716.3372723
Other Links: academic.microsoft.com|arxiv.org

Abstract:

We revisit the notion of individual fairness proposed by Dwork et al. A central challenge in operationalizing their approach is the difficulty in eliciting a human specification of a similarity metric. In this paper, we propose an operationalization of individual fairness that does not rely on a human specification of a distance metric....More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments