Retour aux activités
Discussion DS4DM autour d'un café

Robust Counterfactual Explanations for Random Forests

iCalendar

20 mai 2022   11h00 — 13h00

Alexandre Forel Polytechnique Montréal, Canada

Alexandre Forel

Séminaire hybrique sur Zoom et dans la salle de séminaire du GERAD.

Counterfactual explanations describe how to modify a feature vector to flip the outcome of a trained classifier. Several methods have been proposed to generate counterfactual explanations, but their robustness when the classifier is re-trained has not been studied so far. Our goal is to obtain counterfactual explanations for random forests that are robust to algorithmic uncertainty. We study the link between the robustness of ensemble models and base learners and formulate a chance-constrained optimization model. We provide statistical guarantees for random forests of stumps and develop a practical method with good performance. We show that existing naive and plausibility-based methods provide surprisingly low robustness. Our method achieves the best trade-off between robustness and the distance of counterfactual explanations to the initial observation.

Séminaire conjoint avec Dounia Lakhmiri.

Federico Bobbio responsable
Gabriele Dragotto responsable

Lieu

Séminaire hybride
Zoom et salle 4488
Pavillon André-Aisenstadt
Campus de l'Université de Montréal
2920, chemin de la Tour
Montréal Québec H3T 1J4 Canada

Organisme associé

Axe de recherche

Application de recherche