Stępka, IgnacyLango, MateuszStefanowski, Jerzy2023-09-212023-09-212023Stępka 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: 10.34658/9788366741928.18.978-83-66741-92-8http://hdl.handle.net/11652/4793https://doi.org/10.34658/9788366741928.18Counterfactual 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.enDla wszystkich w zakresie dozwolonego użytkuFair use conditionexplainable AIcounterfactual explanationsmultiple evaluation criteriadominance relationwyjaśnialna sztuczna inteligencjawyjaśnienia kontrfaktycznewiele kryteriów ocenyrelacja dominacjiRozdział - monografiaLicencja PŁLUT License10.34658/9788366741928.18