Abstract
We revisit the notion of individual fairness first proposed by Dwork et al. [2012], which asks that "similar individuals should be treated similarly". A primary difficulty with this definition is that it assumes a completely specified fairness metric for the task at hand. In contrast, we consider a framework for fairness elicitation, in which fairness is indirectly specified only via a sample of pairs of individuals who should be treated (approximately) equally on the task. We make no assumption that these pairs are consistent with any metric. We provide a provably convergent oracle-efficient algorithm for minimizing error subject to the fairness constraints, and prove generalization theorems for both accuracy and fairness. Since the constrained pairs could be elicited either from a panel of judges, or from particular individuals, our framework provides a means for algorithmically enforcing subjective notions of fairness. Because we perform this as a one-shot task, rather than first trying to learn a metric consistent with the elicited judgements, we avoid having to make any assumptions on the form of the elicited judgements to give generalization bounds. We report on preliminary findings of a behavioral study of subjective fairness using human-subject fairness constraints elicited on the COMPAS criminal recidivism dataset. Joint work with Christopher Jung, Michael Kearns, Seth Neel, Logan Stapleton, and Zhiwei Steven Wu