Explaining Cautious Random Forests via Counterfactuals - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Explaining Cautious Random Forests via Counterfactuals

Résumé

Cautious random forests are designed to make indeterminate decisions when tree outputs are conflicting. Since indeterminacy has a cost, it seems desirable to highlight why a precise decision could not be made for an instance, or which minimal modifications can be made to the instance so that the decision becomes a single class. In this paper, we apply an efficient extractor to generate determinate counterfactual examples of different classes, which are used to explain indeterminacy. We evaluate the efficiency of our strategy on different datasets and we illustrate it on two simple case studies involving both tabular and image data.
Fichier principal
Vignette du fichier
SMPS2022_paper_04.pdf (259.48 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03895233 , version 1 (12-12-2022)

Identifiants

Citer

Haifei Zhang, Benjamin Quost, Marie-Hélène Masson. Explaining Cautious Random Forests via Counterfactuals. 10th International Conference on Soft Methods in Probability and Statistics (SMPS 2022), Sep 2022, Valladolid, Spain. pp.390-397, ⟨10.1007/978-3-031-15509-3_51⟩. ⟨hal-03895233⟩
28 Consultations
43 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More