Counterfactually Fair Conformal Prediction
This addresses fairness in uncertainty quantification for decision-making under uncertainty, offering a training-free method, though it is incremental as it extends existing fairness and conformal prediction concepts.
The paper tackles the lack of counterfactual fairness in prediction sets from conformal prediction by developing Counterfactually Fair Conformal Prediction (CF-CP), which produces counterfactually fair prediction sets while maintaining marginal coverage with minimal increase in set size on synthetic and real datasets.
While counterfactual fairness of point predictors is well studied, its extension to prediction sets--central to fair decision-making under uncertainty--remains underexplored. On the other hand, conformal prediction (CP) provides efficient, distribution-free, finite-sample valid prediction sets, yet does not ensure counterfactual fairness. We close this gap by developing Counterfactually Fair Conformal Prediction (CF-CP) that produces counterfactually fair prediction sets. Through symmetrization of conformity scores across protected-attribute interventions, we prove that CF-CP results in counterfactually fair prediction sets while maintaining the marginal coverage property. Furthermore, we empirically demonstrate that on both synthetic and real datasets, across regression and classification tasks, CF-CP achieves the desired counterfactual fairness and meets the target coverage rate with minimal increase in prediction set size. CF-CP offers a simple, training-free route to counterfactually fair uncertainty quantification.