From Contrastive to Abductive Explanations and Back Again
Résumé
Explanations of Machine Learning (ML) models often address a Open image in new window question. Such explanations can be related with selecting feature-value pairs which are sufficient for the prediction. Recent work has investigated explanations that address a Open image in new window question, i.e. finding a change of feature values that guarantee a change of prediction. Given their goals, these two forms of explaining predictions of ML models appear to be mostly unrelated. However, this paper demonstrates otherwise, and establishes a rigorous formal relationship between Open image in new window and Open image in new window explanations. Concretely, the paper proves that, for any given instance, Open image in new window explanations are minimal hitting sets of Open image in new window explanations and vice-versa. Furthermore, the paper devises novel algorithms for extracting and enumerating both forms of explanations.
Domaines
Apprentissage [cs.LG]
Fichier principal
From Contrastive To Abductive Explanations and Back Again.pdf (768.16 Ko)
Télécharger le fichier
Origine | Fichiers produits par l'(les) auteur(s) |
---|