On Relating Why and Why not explanations - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

On Relating Why and Why not explanations

Résumé

Explanations of Machine Learning (ML) models often address a 'Why?' 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 'Why Not?' 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 'Why?' and 'Why Not?' explanations. Concretely, the paper proves that, for any given instance, 'Why?' explanations are minimal hitting sets of 'Why Not?' explanations and vice-versa. Furthermore, the paper devises novel algorithms for extracting and enumerating both forms of explanations.

Dates et versions

hal-03159201 , version 1 (04-03-2021)

Licence

Paternité

Identifiants

Citer

Alexey Ignatiev, Nina Narodytska, Nicholas Asher, Joao Marques-Silva. On Relating Why and Why not explanations. 2021. ⟨hal-03159201⟩
34 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More