Feasible and Desirable Counterfactual Generation by Preserving Human Defined Constraints
This work addresses the challenge of producing actionable and desirable explanations for end-users and domain experts in machine learning, though it is incremental in combining existing constraint types.
The paper tackles the problem of generating counterfactual explanations that adhere to human-defined feasibility constraints, showing that incorporating causal constraints leads to significantly better explanations in terms of feasibility and desirability for users.
We present a human-in-the-loop approach to generate counterfactual (CF) explanations that preserve global and local feasibility constraints. Global feasibility constraints refer to the causal constraints that are necessary for generating actionable CF explanation. Assuming a domain expert with knowledge on unary and binary causal constraints, our approach efficiently employs this knowledge to generate CF explanation by rejecting gradient steps that violate these constraints. Local feasibility constraints encode end-user's constraints for generating desirable CF explanation. We extract these constraints from the end-user of the model and exploit them during CF generation via user-defined distance metric. Through user studies, we demonstrate that incorporating causal constraints during CF generation results in significantly better explanations in terms of feasibility and desirability for participants. Adopting local and global feasibility constraints simultaneously, although improves user satisfaction, does not significantly improve desirability of the participants compared to only incorporating global constraints.