Hybrid Recommender System based on Autoencoders
This is an incremental improvement for recommender systems, particularly benefiting cold-start scenarios.
The paper tackled the problem of matrix completion in recommender systems by enhancing an autoencoder-based architecture with a loss function for missing values and side information, resulting in slight overall test error improvements and more significant impacts on cold users/items.
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.