Back to activities
DS4DM Coffee Talk

Robust Counterfactual Explanations for Random Forests

iCalendar

May 20, 2022   11:00 AM — 01:00 PM

Alexandre Forel Polytechnique Montréal, Canada

Alexandre Forel

Hybrid seminar on Zoom and in the GERAD seminar room.

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.

Joint seminar with Dounia Lakhmiri.

Federico Bobbio organizer
Gabriele Dragotto organizer

Location

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

Associated organizations

Research Axis

Research application