SHAFF: Fast and consistent SHApley eFfect estimates via random Forests - Département de mathématiques appliquées Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

SHAFF: Fast and consistent SHApley eFfect estimates via random Forests

Résumé

Interpretability of learning algorithms is crucial for applications involving critical decisions, and variable importance is one of the main interpretation tools. Shapley effects are now widely used to interpret both tree ensembles and neural networks, as they can efficiently handle dependence and interactions in the data, as opposed to most other variable importance measures. However, estimating Shapley effects is a challenging task, because of the computational complexity and the conditional expectation estimates. Accordingly, existing Shapley algorithms have flaws: a costly running time, or a bias when input variables are dependent. Therefore, we introduce SHAFF, SHApley eFfects via random Forests, a fast and accurate Shapley effect estimate, even when input variables are dependent. We show SHAFF efficiency through both a theoretical analysis of its consistency, and the practical performance improvements over competitors with extensive experiments. An implementation of SHAFF in C++ and R is available online.
Fichier principal
Vignette du fichier
shaff_arxiv.pdf (666.9 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03232621 , version 1 (21-05-2021)
hal-03232621 , version 2 (18-10-2021)
hal-03232621 , version 3 (02-02-2022)

Identifiants

Citer

Clément Bénard, Gérard Biau, Sébastien da Veiga, Erwan Scornet. SHAFF: Fast and consistent SHApley eFfect estimates via random Forests. 2021. ⟨hal-03232621v2⟩
214 Consultations
286 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More