Communication Dans Un Congrès Année : 2024

Deriving Provably Correct Explanations for Decision Trees: The Impact of Domain Theories

Résumé

We are interested in identifying the complexity of computing local explanations of various types given a decision tree, when the Boolean conditions used in the tree are not independent. This is usually the case when decision trees are learned from instances described using numerical or categorical attributes. In such a case, considering the domain theory indicating how the Boolean conditions occurring in the tree are logically connected is paramount to derive provably correct explanations. However, the nature of the domain theory may have a strong impact on the complexity of generating explanations. In this paper, we identify the complexity of deriving local explanations (abductive or contrastive) given a decision tree in the general case, and under several natural restrictions about the domain theory.

Fichier principal
Vignette du fichier
audemard-lagniez-marquis-szczepanski-ijcai24-impact-theory.pdf (392.89 Ko) Télécharger le fichier

Dates et versions

hal-04680413 , version 1 (28-08-2024)

Licence

Identifiants

  • HAL Id : hal-04680413 , version 1

Citer

Gilles Audemard, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski. Deriving Provably Correct Explanations for Decision Trees: The Impact of Domain Theories. The 33rd International Joint Conference on Artificial Intelligence, Aug 2024, Jeju Island (South Korea), South Korea. pp.3688-3696. ⟨hal-04680413⟩
82 Consultations
189 Téléchargements

Partager

  • More