Hybrid Recommender System based on Autoencoders

24 Jun 2016  ·  Florian Strub, Romaric Gaudel, Jérémie Mary ·

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.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Recommendation Systems Douban I-CFN RMSE 0.6911 # 1
Recommendation Systems Douban U-CFN RMSE 0.7049 # 2
Recommendation Systems MovieLens 10M I-CFN RMSE 0.7767 # 8
Recommendation Systems MovieLens 10M U-CFN RMSE 0.7954 # 11
Recommendation Systems MovieLens 1M U-CFN RMSE 0.8574 # 12
Recommendation Systems MovieLens 1M I-CFN RMSE 0.8321 # 7


No methods listed for this paper. Add relevant methods here