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.
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://hal.inria.fr/hal-01256422
Contributor : Jérémie Mary <>
Submitted on : Thursday, January 14, 2016 - 5:34:05 PM
Last modification on : Friday, March 22, 2019 - 1:35:49 AM
Long-term archiving on : Friday, November 11, 2016 - 6:31:44 AM

File

Collaborative Filtering with S...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01256422, version 1

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⟩

Share

Metrics

Record views

2826

Files downloads

6366