Timezone: »

Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions
Hao Wang · Berk Ustun · Flavio Calmon

Thu Jun 13 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #136

When the performance of a machine learning model varies over groups defined by sensitive attributes (e.g., gender or ethnicity), the performance disparity can be expressed in terms of the probability distributions of the input and output variables over each group. In this paper, we exploit this fact to reduce the disparate impact of a fixed classification model over a population of interest. Given a black-box classifier, we aim to eliminate the performance gap by perturbing the distribution of input variables for the disadvantaged group. We refer to the perturbed distribution as a counterfactual distribution, and characterize its properties for common fairness criteria. We introduce a descent algorithm to learn a counterfactual distribution from data. We then discuss how the estimated distribution can be used to build a data preprocessor that can reduce disparate impact without training a new model. We validate our approach through experiments on real-world datasets, showing that it can repair different forms of disparity without a significant drop in accuracy.

Author Information

Hao Wang (Harvard University)
Berk Ustun (Harvard University)
Flavio Calmon (Harvard University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors