Optimal Transport Group Counterfactual Explanations
This addresses the need for interpretable and efficient counterfactual explanations in machine learning, particularly for group-based scenarios, though it is incremental as it builds on existing counterfactual explanation methods.
The paper tackles the problem of generating group counterfactual explanations by learning an optimal transport map that generalizes to new group members without re-optimization, resulting in accurate generalization, preserved group geometry, and negligible additional transport cost compared to baselines.
Group counterfactual explanations find a set of counterfactual instances to explain a group of input instances contrastively. However, existing methods either (i) optimize counterfactuals only for a fixed group and do not generalize to new group members, (ii) strictly rely on strong model assumptions (e.g., linearity) for tractability or/and (iii) poorly control the counterfactual group geometry distortion. We instead learn an explicit optimal transport map that sends any group instance to its counterfactual without re-optimization, minimizing the group's total transport cost. This enables generalization with fewer parameters, making it easier to interpret the common actionable recourse. For linear classifiers, we prove that functions representing group counterfactuals are derived via mathematical optimization, identifying the underlying convex optimization type (QP, QCQP, ...). Experiments show that they accurately generalize, preserve group geometry and incur only negligible additional transport cost compared to baseline methods. If model linearity cannot be exploited, our approach also significantly outperforms the baselines.