Integrating Prior Knowledge in Post-hoc Explanations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Integrating Prior Knowledge in Post-hoc Explanations

Résumé

In the field of explainable artificial intelligence (XAI), post hoc interpretability methods aim at explaining to a user the predictions of a trained decision model. Integrating prior knowledge into such interpretability methods aims at improving the explanation understandability and allowing for personalised explanations adapted to each user. In this paper, we propose to define a cost function that explicitly integrates prior knowledge into the interpretability objectives: we present a general framework for the optimization problem of post-hoc interpretability methods, and show that user knowledge can thus be integrated to any method by adding a compatibility term in the cost function. We instantiate the proposed formalization in the case of counterfactual explanations and propose a new interpretability method called Knowledge Integration in Counterfactual Explanation (KICE) to optimize it. The paper performs an experimental study on several benchmark data sets to characterize the counterfactual instances generated by KICE, as compared to reference methods.
Fichier principal
Vignette du fichier
IPMU_prior_knowledge.pdf (414.01 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03728133 , version 1 (20-07-2022)

Identifiants

Citer

Adulam Jeyasothy, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki. Integrating Prior Knowledge in Post-hoc Explanations. Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU'2022), Jul 2022, Milan, Italy. pp.707-719, ⟨10.1007/978-3-031-08974-9_56⟩. ⟨hal-03728133⟩
59 Consultations
40 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More