Counterfactual Plans under Distributional Ambiguity
This work addresses the robustness of counterfactual explanations for machine learning models in consequential domains, but it is incremental as it builds on existing methods with specific adjustments.
The paper tackles the problem of counterfactual plans becoming ineffective due to model updates by studying them under distributional ambiguity, proposing bounds for validity probability and corrective methods that improve robustness, with numerical validation on real-world datasets.
Counterfactual explanations are attracting significant attention due to the flourishing applications of machine learning models in consequential domains. A counterfactual plan consists of multiple possibilities to modify a given instance so that the model's prediction will be altered. As the predictive model can be updated subject to the future arrival of new data, a counterfactual plan may become ineffective or infeasible with respect to the future values of the model parameters. In this work, we study the counterfactual plans under model uncertainty, in which the distribution of the model parameters is partially prescribed using only the first- and second-moment information. First, we propose an uncertainty quantification tool to compute the lower and upper bounds of the probability of validity for any given counterfactual plan. We then provide corrective methods to adjust the counterfactual plan to improve the validity measure. The numerical experiments validate our bounds and demonstrate that our correction increases the robustness of the counterfactual plans in different real-world datasets.