Fairness Through Computationally-Bounded Awareness

Authors:
Michael Kim Stanford University
Omer Reingold Stanford University
Guy Rothblum Weizmann Institute of Science

Introduction:

The authors study the problem of fair classification within the versatile framework of Dwork et al.

Abstract:

We study the problem of fair classification within the versatile framework of Dwork et al. [ITCS '12], which assumes the existence of a metric that measures similarity between pairs of individuals. Unlike earlier work, we do not assume that the entire metric is known to the learning algorithm; instead, the learner can query this arbitrary metric a bounded number of times. We propose a new notion of fairness called metric multifairness and show how to achieve this notion in our setting.Metric multifairness is parameterized by a similarity metric d on pairs of individuals to classify and a rich collection C of (possibly overlapping) "comparison sets" over pairs of individuals. At a high level, metric multifairness guarantees that similar subpopulations are treated similarly, as long as these subpopulations are identified within the class C.

You may want to know: