Feasible and Desirable Counterfactual Generation by Preserving Human Defined Constraints

TL;DR

This paper introduces a human-in-the-loop method for generating counterfactual explanations that respect both causal and user-defined constraints, improving the feasibility and desirability of explanations.

Contribution

It proposes a novel approach that integrates global causal constraints and local user constraints into counterfactual generation, enhancing explanation quality.

Findings

Incorporating causal constraints improves explanation feasibility.

User satisfaction increases with combined local and global constraints.

Global constraints alone significantly enhance explanation desirability.

Abstract

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.