Explanations for Monotonic Classifiers - Université Toulouse III - Paul Sabatier - Toulouse INP Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Explanations for Monotonic Classifiers

Résumé

In many classification tasks there is a requirement of monotonicity. Concretely, if all else remains constant, increasing (resp. decreasing) the value of one or more features must not decrease (resp. increase) the value of the prediction. Despite comprehensive efforts on learning monotonic classifiers, dedicated approaches for explaining monotonic classifiers are scarce and classifierspecific. This paper describes novel algorithms for the computation of one formal explanation of a (black-box) monotonic classifier. These novel algorithms are polynomial in the run time complexity of the classifier and the number of features. Furthermore, the paper presents a practically efficient model-agnostic algorithm for enumerating formal explanations.
Fichier principal
Vignette du fichier
marques-silva21a.pdf (308 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03311393 , version 1 (31-07-2021)

Licence

Paternité

Identifiants

Citer

Joao Marques-Silva, Thomas Gerspacher, Martin Cooper, Alexey Ignatiev, Nina Narodytska. Explanations for Monotonic Classifiers. 38th International Conference on Machine Learning (ICML 2021), 2021, virtual, Austria. ⟨hal-03311393⟩
73 Consultations
27 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More