Finding Counterfactual Explanations through Constraint Relaxations
This addresses the need for more informative explanations in constraint satisfaction problems, but it is incremental as it adapts existing counterfactual explanation concepts from machine learning to this domain.
The paper tackles the problem of infeasibility in interactive constraint systems by proposing an iterative method to compute counterfactual explanations, which suggest changes to constraints rather than removing them, though no concrete results or numbers are provided.
Interactive constraint systems often suffer from infeasibility (no solution) due to conflicting user constraints. A common approach to recover infeasibility is to eliminate the constraints that cause the conflicts in the system. This approach allows the system to provide an explanation as: "if the user is willing to drop out some of their constraints, there exists a solution". However, one can criticise this form of explanation as not being very informative. A counterfactual explanation is a type of explanation that can provide a basis for the user to recover feasibility by helping them understand which changes can be applied to their existing constraints rather than removing them. This approach has been extensively studied in the machine learning field, but requires a more thorough investigation in the context of constraint satisfaction. We propose an iterative method based on conflict detection and maximal relaxations in over-constrained constraint satisfaction problems to help compute a counterfactual explanation.