Paper Info
Title
Discriminative but Not Discriminatory: A Comparison of Fairness Definitions under Different Worldviews.
Abstract
We mathematically compare three competing definitions of group-level nondiscrimination: demographic parity, equalized odds, and calibration. Using the theoretical framework of Friedler et al., we study the properties of each definition under various worldviews, which are assumptions about how, if at all, the observed data is biased. We prove that different worldviews call for different definitions of fairness, and we specify when it is appropriate to use demographic parity and equalized odds. In addition, we argue that calibration is unsuitable for the purpose of ensuring nondiscrimination. Finally, we define a worldview that is more realistic than the previously considered ones, and we introduce a new notion of fairness that is suitable for this worldview.
Year
Venue
Field
2018
arXiv: Learning
Theoretical computer science,Artificial intelligence,Odds,Parity (mathematics),Discriminative model,Mathematics,Machine learning
DocType
Volume
Citations 
Journal
abs/1808.08619
0
PageRank 
References 
Authors
0.34
6
2
Name
Order
Citations
PageRank
Samuel Yeom121.71
Michael Carl Tschantz246631.72