Convex Density Constraints for Computing Plausible Counterfactual Explanations
This work addresses the need for user-friendly explanations in ML, particularly under regulations like GDPR, by improving plausibility in counterfactual explanations, though it is incremental as it builds on recent research.
The paper tackles the problem of computing plausible and feasible counterfactual explanations for machine learning models by proposing convex density constraints to ensure high-density regions in the data space, resulting in an efficient method for generating such explanations.
The increasing deployment of machine learning as well as legal regulations such as EU's GDPR cause a need for user-friendly explanations of decisions proposed by machine learning models. Counterfactual explanations are considered as one of the most popular techniques to explain a specific decision of a model. While the computation of "arbitrary" counterfactual explanations is well studied, it is still an open research problem how to efficiently compute plausible and feasible counterfactual explanations. We build upon recent work and propose and study a formal definition of plausible counterfactual explanations. In particular, we investigate how to use density estimators for enforcing plausibility and feasibility of counterfactual explanations. For the purpose of efficient computations, we propose convex density constraints that ensure that the resulting counterfactual is located in a region of the data space of high density.