On Usefulness of Dominance Relation for Selecting Counterfactuals from the Ensemble of Explainers
Data
2023
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
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.
Opis
Słowa kluczowe
explainable AI, counterfactual explanations, multiple evaluation criteria, dominance relation, wyjaśnialna sztuczna inteligencja, wyjaśnienia kontrfaktyczne, wiele kryteriów oceny, relacja dominacji
Cytowanie
Stępka I., Lango M., Stefanowski J., On Usefulness of Dominance Relation for Selecting Counterfactuals from the Ensemble of Explainers. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 125-130, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.18.