Hybrid Collaborative Filtering with Autoencoders

TL;DR

This paper introduces CFN, a neural network architecture for collaborative filtering that models non-linear matrix factorization, leveraging side information to improve recommendation accuracy, demonstrated on MovieLens and Douban datasets.

Contribution

The paper presents a novel neural network-based collaborative filtering model that effectively incorporates side information and outperforms existing methods.

Findings

CFN outperforms state-of-the-art methods on benchmark datasets.

Incorporating side information improves recommendation quality.

CFN demonstrates the potential of neural networks in collaborative filtering.

Abstract

Collaborative Filtering aims at exploiting the feedback of users to provide personalised recommendations. Such algorithms look for latent variables in a large sparse matrix of ratings. They can be enhanced by adding side information to tackle the well-known cold start problem. While Neu-ral Networks have tremendous success in image and speech recognition, they have received less attention in Collaborative Filtering. This is all the more surprising that Neural Networks are able to discover latent variables in large and heterogeneous datasets. In this paper, we introduce a Collaborative Filtering Neural network architecture aka CFN which computes a non-linear Matrix Factorization from sparse rating inputs and side information. We show experimentally on the MovieLens and Douban dataset that CFN outper-forms the state of the art and benefits from side information. We provide an implementation of the algorithm as a reusable plugin for Torch, a popular Neural Network framework.