Hybrid Recommender System based on Autoencoders

Florian Strub 1, 2 Romaric Gaudel 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 : A standard model for Recommender Systems is the Matrix Completion setting: given partially known matrix of ratings given by users (rows) to items (columns), infer the unknown ratings. In the last decades, few attempts where done to handle that objective with Neural Networks, but recently an architecture based on Autoencoders proved to be a promising approach. In current paper, we enhanced that architecture (i) by using a loss function adapted to input data with missing values, and (ii) by incorporating side information. The experiments demonstrate that while side information only slightly improve the test error averaged on all users/items, it has more impact on cold users/items.
Document type :
Conference papers
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download

https://hal.inria.fr/hal-01336912
Contributor : Romaric Gaudel <>
Submitted on : Friday, December 2, 2016 - 11:00:17 AM
Last modification on : Friday, March 22, 2019 - 1:35:22 AM
Long-term archiving on : Wednesday, March 22, 2017 - 11:53:17 PM

Files

AutoEnc.pdf
Files produced by the author(s)

Licence


Copyright

Identifiers

Citation

Florian Strub, Romaric Gaudel, Jérémie Mary. Hybrid Recommender System based on Autoencoders. the 1st Workshop on Deep Learning for Recommender Systems, Sep 2016, Boston, United States. pp.11 - 16, ⟨10.1145/2988450.2988456⟩. ⟨hal-01336912v2⟩

Share

Metrics

Record views

452

Files downloads

1835