AutoXAI: A Framework to Automatically Select the Most Adapted XAI Solution - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

AutoXAI: A Framework to Automatically Select the Most Adapted XAI Solution

Résumé

A large number of XAI (eXplainable Artificial Intelligence) solutions have been proposed in recent years. Recently, thanks to new XAI evaluation metrics, it has become possible to compare these XAI solutions. However, selecting the most relevant XAI solution among all this diversity is still a tedious task, especially if a user has specific needs and constraints. In this paper, we propose AutoXAI, a framework that recommends the best XAI solution and its hyperparameters according to specified XAI evaluation metrics while considering the user's context (dataset, machine learning model, XAI needs and constraints). It adapts approaches from context-aware recommender systems on one side and strategies of optimization and evaluation from AutoML (Automated Machine Learning) on the other. Through two use cases, we show that AutoXAI recommends XAI solutions adapted to the user's needs with the best hyperparameters matching the user's constraints. CCS CONCEPTS • Computing methodologies → Machine learning.
Fichier principal
Vignette du fichier
AutoXAI_CIKM-2.pdf (810 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03854778 , version 1 (16-11-2022)

Identifiants

Citer

Robin Cugny, Julien Aligon, Max Chevalier, Geoffrey Roman Jimenez, Olivier Teste. AutoXAI: A Framework to Automatically Select the Most Adapted XAI Solution. 31st ACM International Conference on Information and Knowledge Management (CIKM 2022), Oct 2022, Atlanta GA, United States. pp.315-324, ⟨10.1145/3511808.3557247⟩. ⟨hal-03854778⟩
90 Consultations
255 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More