The Backfire Effects of Fairness Constraints

Recently, the fairness community has shifted from achieving one-shot fair decisions to striving for long-term fairness. In this work, we propose a metric to measure the long-term impact of a policy on the target variable distributions. We theoretically characterize the conditions underwhich threshold policies could lead to a backfire on population groups. We conduct experiments with a set of well-used fairness constraints onboth synthetic and real-world datasets.