摘要：There has been much discussion concerning how "fairness" should be measured or enforced in classification. Individual Fairness [Dwork et al., 2012], which requires that similar individuals be treated similarly, is a highly appealing definition as it gives strong treatment guarantees for individuals. Unfortunately, the need for a task-specific similarity metric has prevented its use in practice. In this work, we propose a solution to the problem of approximating a metric for Individual Fairness based on human judgments. Our model assumes access to a human fairness arbiter who is free of explicit biases and possesses sufficient domain knowledge to evaluate similarity. Our contributions include definitions for metric approximation relevant for Individual Fairness, constructions for approximations from a limited number of realistic queries to the arbiter on a sample of individuals, and learning procedures to construct hypotheses for metric approximations which generalize to unseen samples under certain assumptions of learnability of distance threshold functions.
