Neural Architecture Search for Extreme Multi-label Text Classification - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2020

Neural Architecture Search for Extreme Multi-label Text Classification

Résumé

Extreme classification and Neural Architecture Search (NAS) are research topics, which have gain a lot of interest recently. While the former has mainly been motivated and applied in e-commerce and Natural Language Processing (NLP) applications, the NAS approach has been applied to a small variety of tasks, mainly in image processing. In this study, we extend the scope of NAS to the extreme multi-label classification (XMC) tasks. We propose a neuro-evolution approach, that has been found most suitable for a variety of tasks. Our NAS method automatically finds architectures that give competitive results to the state of the art (and superior to other methods) with faster convergence. Furthermore, the weights of the architecture blocks have been analyzed to give insight on the importance of the various operations that have been selected by the method.
Fichier principal
Vignette du fichier
XMCNAS.pdf (102.16 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03177271 , version 1 (23-03-2021)

Identifiants

Citer

Loc Pauletto, Massih-Reza Amini, Rohit Babbar, Nicolas Winckler. Neural Architecture Search for Extreme Multi-label Text Classification. Neural Information Processing 27th International Conference, ICONIP 2020, Bangkok, Thailand, November 23–27, 2020, Proceedings,, , pp.282-293, 2020, ⟨10.1007/978-3-030-63836-8_24⟩. ⟨hal-03177271⟩
105 Consultations
255 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More