On the failings of Shapley values for explainability

Explainable Artificial Intelligence (XAI) is widely considered to be critical for building trust into the deployment of systems that integrate the use of machine learning (ML) models. For more than two decades Shapley values have been used as the theoretical underpinning for some methods of XAI, bei...

Full description

Bibliographic Details

Published in:	International journal of approximate reasoning Vol. 171; p. 109112
Main Authors:	Huang, Xuanxiang, Marques-Silva, Joao
Format:	Journal Article
Language:	English
Published:	Elsevier Inc 01.08.2024
Subjects:	Abductive explanations Explainable AI (XAI) SHAP scores Shapley values Shapley values SHAP scores Abductive explanations Explainable AI (XAI)
ISSN:	0888-613X, 1873-4731
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!