Finding Counterfactual Explanations through Constraint Relaxations

TL;DR

This paper introduces an iterative method for generating counterfactual explanations in over-constrained constraint satisfaction problems by detecting conflicts and applying maximal relaxations, enhancing user understanding of feasible solutions.

Contribution

It presents a novel iterative approach for computing counterfactual explanations through conflict detection and constraint relaxation in constraint satisfaction problems.

Findings

Effective identification of conflicting constraints.

Successful computation of counterfactual explanations.

Improved user guidance for feasible solutions.

Abstract

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.