Hybrid Recommender System based on Autoencoders

TL;DR

This paper improves autoencoder-based recommender systems by adapting loss functions for missing data and incorporating side information, showing benefits especially for cold-start users and items.

Contribution

It introduces a novel autoencoder architecture with a specialized loss function and side information integration for better recommendations.

Findings

Side information slightly improves overall test error.

Significant impact of side information on cold users/items.

Enhanced autoencoder architecture outperforms previous models.

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.