On usefulness of dominance relation for selecting counterfactuals from the ensemble of explainers
[ 1 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ P ] employee
2023
chapter in monograph / paper
english
- Explainable AI
- Counterfactual explanations
- Multiple evaluation criteria
- Dominance relation
EN Counterfactual explanations are widely used to explain ML model predictions by providing alternative scenarios. However, choosing the most appropriate explanation method and one of generated counterfactuals is not an easy task. In this paper, we propose an approach that filters out a large set of counterfactuals generated by a set of diverse algorithms through a multi-criteria subset selection problem solved using the dominance relation. Experiments show that exploiting the dominance relation results in a concise set of counterfactual explanations.
125 - 130
dla wszystkich w zakresie dozwolonego użytku
open repository
final published version
at the time of publication
20