Challenges in interpretability of additive models
No Thumbnail Available
Access rights
openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A4 Artikkeli konferenssijulkaisussa
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Authors
Date
2024
Department
Major/Subject
Mcode
Degree programme
Language
en
Pages
Series
Abstract
We review generalized additive models as a type of ‘transparent’ model that has recently seen renewed interest in the deep learning community as neural additive models. We highlight multiple types of nonidentifiability in this model class and discuss challenges in interpretability, arguing for restraint when claiming ‘interpretability’ or ‘suitability for safety-critical applications’ of such models.Description
| openaire: EC/H2020/951847/EU//ELISE
Keywords
Other note
Citation
Zhang, X, Martinelli, J & John, T 2024, ' Challenges in interpretability of additive models ', Paper presented at Workshop on Explainable Artificial Intelligence, Virtual, Online, 14/08/2024 - 15/08/2024 . < https://drive.google.com/file/d/1ap0WJGnUMGz1GAZaqPQsjSq0RgZZWB9v/view?usp=sharing >