Timezone: »

Two Simple Ways to Learn Individual Fairness Metrics from Data
Debarghya Mukherjee · Mikhail Yurochkin · Moulinath Banerjee · Yuekai Sun

Tue Jul 14 09:00 AM -- 09:45 AM & Tue Jul 14 09:00 PM -- 09:45 PM (PDT) @

Individual fairness is an intuitive definition of algorithmic fairness that addresses some of the drawbacks of group fairness. Despite its benefits, it depends on a task specific fair metric that encodes our intuition of what is fair and unfair for the ML task at hand, and the lack of a widely accepted fair metric for many ML tasks is the main barrier to broader adoption of individual fairness. In this paper, we present two simple ways to learn fair metrics from a variety of data types. We show empirically that fair training with the learned metrics leads to improved fairness on three machine learning tasks susceptible to gender and racial biases. We also provide theoretical guarantees on the statistical performance of both approaches.

Author Information

Debarghya Mukherjee (University of Michigan)
Mikhail Yurochkin (IBM Research AI)
Moulinath Banerjee (University of Michigan)
Yuekai Sun (University of Michigan)

More from the Same Authors