On Binary Reduction of Large-scale Multiclass Classification Problems

Abstract : In the context of large-scale problems, traditional multiclass classification approaches have to deal with class imbalancement and complexity issues which make them inoperative in some extreme cases. In this paper we study a transformation that reduces the initial multiclass classification of examples into a binary classification of pairs of examples and classes. We present generalization error bounds that exhibit the interdependency between the pairs of examples and which recover known results on binary classification with i.i.d. data. We show the efficiency of the deduced algorithm compared to state-of-the-art multiclass classification strategies on two large-scale document collections especially in the interesting case where the number of classes becomes very large.
Type de document :
Communication dans un congrès
Fourteenth International Symposium on Intelligent Data Analysis (IDA 2015), Oct 2015, Saint-Etienne, France. <https://ida2015.univ-st-etienne.fr/>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01236588
Contributeur : Massih-Reza Amini <>
Soumis le : mardi 1 décembre 2015 - 21:58:25
Dernière modification le : mardi 21 février 2017 - 01:07:50

Identifiants

  • HAL Id : hal-01236588, version 1

Citation

Bikash Joshi, Massih-Reza Amini, Ioannis Partalas, Liva Ralaivola, Nicolas Usunier, et al.. On Binary Reduction of Large-scale Multiclass Classification Problems. Fourteenth International Symposium on Intelligent Data Analysis (IDA 2015), Oct 2015, Saint-Etienne, France. <https://ida2015.univ-st-etienne.fr/>. <hal-01236588>

Partager

Métriques

Consultations de la notice

115