Rule Extraction with Guaranteed Fidelity

Abstract : This paper extends the conformal prediction framework to rule extraction, making it possible to extract interpretable models from opaque models in a setting where either the infidelity or the error rate is bounded by a predefined significance level. Experimental results on 27 publicly available data sets show that all three setups evaluated produced valid and rather efficient conformal predictors. The implication is that augmenting rule extraction with conformal prediction allows extraction of models where test set errors or test sets infidelities are guaranteed to be lower than a chosen acceptable level. Clearly this is beneficial for both typical rule extraction scenarios, i.e., either when the purpose is to explain an existing opaque model, or when it is to build a predictive model that must be interpretable.
Type de document :
Communication dans un congrès
Lazaros Iliadis; Ilias Maglogiannis; Harris Papadopoulos; Spyros Sioutas; Christos Makris. 10th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2014, Rhodes, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-437, pp.281-290, 2014, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-662-44722-2_30〉
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01391055
Contributeur : Hal Ifip <>
Soumis le : mercredi 2 novembre 2016 - 17:18:43
Dernière modification le : vendredi 1 décembre 2017 - 01:16:37
Document(s) archivé(s) le : vendredi 3 février 2017 - 14:42:03

Fichier

978-3-662-44722-2_30_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Ulf Johansson, Rikard König, Henrik Linusson, Tuve Löfström, Henrik Boström. Rule Extraction with Guaranteed Fidelity. Lazaros Iliadis; Ilias Maglogiannis; Harris Papadopoulos; Spyros Sioutas; Christos Makris. 10th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2014, Rhodes, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-437, pp.281-290, 2014, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-662-44722-2_30〉. 〈hal-01391055〉

Partager

Métriques

Consultations de la notice

42

Téléchargements de fichiers

6