Superhuman Fairness
This addresses fairness in ML decisions for applications where human decisions are suboptimal, offering a novel approach but likely incremental in impact.
The paper tackles the problem of specifying appropriate performance-fairness trade-offs in machine learning by introducing superhuman fairness, which frames fairness as an imitation learning task to outperform human decisions on multiple performance and fairness metrics, demonstrating benefits with suboptimal decisions.
The fairness of machine learning-based decisions has become an increasingly important focus in the design of supervised machine learning methods. Most fairness approaches optimize a specified trade-off between performance measure(s) (e.g., accuracy, log loss, or AUC) and fairness metric(s) (e.g., demographic parity, equalized odds). This begs the question: are the right performance-fairness trade-offs being specified? We instead re-cast fair machine learning as an imitation learning task by introducing superhuman fairness, which seeks to simultaneously outperform human decisions on multiple predictive performance and fairness measures. We demonstrate the benefits of this approach given suboptimal decisions.