Collaborative Filtering with Stacked Denoising AutoEncoders and Sparse Inputs

Florian Strub 1, 2 Jérémie Mary 1, 2
2 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : Neural networks have not been widely studied in Collaborative Filtering. For instance, no paper using neural networks was published during the Net-flix Prize apart from Salakhutdinov et al's work on Restricted Boltzmann Machine (RBM) [14]. While deep learning has tremendous success in image and speech recognition, sparse inputs received less attention and remains a challenging problem for neural networks. Nonetheless, sparse inputs are critical for collaborative filtering. In this paper, we introduce a neural network architecture which computes a non-linear matrix factorization from sparse rating inputs. We show experimentally on the movieLens and jester dataset that our method performs as well as the best collaborative filtering algorithms. We provide an implementation of the algorithm as a reusable plugin for Torch [4], a popular neural network framework.
Type de document :
Communication dans un congrès
NIPS Workshop on Machine Learning for eCommerce, Dec 2015, Montreal, Canada
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01256422
Contributeur : Jérémie Mary <>
Soumis le : jeudi 14 janvier 2016 - 17:34:05
Dernière modification le : mercredi 25 avril 2018 - 15:43:07
Document(s) archivé(s) le : vendredi 11 novembre 2016 - 06:31:44

Fichier

Collaborative Filtering with S...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01256422, version 1

Collections

Citation

Florian Strub, Jérémie Mary. Collaborative Filtering with Stacked Denoising AutoEncoders and Sparse Inputs. NIPS Workshop on Machine Learning for eCommerce, Dec 2015, Montreal, Canada. 〈hal-01256422v1〉

Partager

Métriques

Consultations de la notice

1927

Téléchargements de fichiers

4107