Reliable Multi-class Classification based on Pairwise Epistemic and Aleatoric Uncertainty

Abstract : We propose a method for reliable prediction in multi-class classification, where reliability refers to the possibility of partial abstention in cases of uncertainty. More specifically, we allow for predictions in the form of preorder relations on the set of classes, thereby generalizing the idea of set-valued predictions. Our approach relies on combining learning by pairwise comparison with a recent proposal for modeling uncertainty in classification, in which a distinction is made between reducible (a.k.a. epistemic) uncertainty caused by a lack of information and irreducible (a.k.a. aleatoric) uncertainty due to intrinsic randomness. The problem of combining uncertain pairwise predictions into a most plausible preorder is then formalized as an integer programming problem. Experimentally, we show that our method is able to appropriately balance reliability and precision of predictions.
Type de document :
Communication dans un congrès
International Joint Conference on Artificial Intelligence, Jul 2018, Stockholm, Sweden
Liste complète des métadonnées

Littérature citée [1 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01815727
Contributeur : Sébastien Destercke <>
Soumis le : jeudi 14 juin 2018 - 14:32:39
Dernière modification le : jeudi 26 juillet 2018 - 15:20:19

Fichier

ijcai18.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01815727, version 1

Collections

Citation

Vu-Linh Nguyen, Sébastien Destercke, Marie-Hélène Masson, Eyke Hüllermeier. Reliable Multi-class Classification based on Pairwise Epistemic and Aleatoric Uncertainty. International Joint Conference on Artificial Intelligence, Jul 2018, Stockholm, Sweden. 〈hal-01815727〉

Partager

Métriques

Consultations de la notice

65

Téléchargements de fichiers

17