Counterfactual Explanations and Model Multiplicity: a Relational Verification View.

We study the interplay between counterfactual explanations and model multiplicity in the context of neural network classifiers. We show that current explanation methods often produce counterfactuals whose validity is not preserved under model multiplicity. We then study the problem of generating counterfactuals that are guaranteed to be robust to model multiplicity, characterise its complexity and propose an approach to solve this problem using ideas from relational verification.