A Survey on Deep Neural Networks in Collaborative Filtering Recommendation Systems

TL;DR

This survey reviews how deep neural networks are applied to improve collaborative filtering recommendation systems, addressing scalability and modeling complex data relationships, and discusses recent advancements, challenges, and future directions.

Contribution

It categorizes and analyzes various deep learning models used in collaborative filtering, providing a comprehensive overview of recent progress and open challenges in the field.

Findings

Deep neural networks enhance CF by modeling complex relationships.

Various DNN architectures like GNN, CNN, RNN improve recommendation accuracy.

The survey identifies key challenges and future research directions.

Abstract

This survey provides an examination of the use of Deep Neural Networks (DNN) in Collaborative Filtering (CF) recommendation systems. As the digital world increasingly relies on data-driven approaches, traditional CF techniques face limitations in scalability and flexibility. DNNs can address these challenges by effectively modeling complex, non-linear relationships within the data. We begin by exploring the fundamental principles of both collaborative filtering and deep neural networks, laying the groundwork for understanding their integration. Subsequently, we review key advancements in the field, categorizing various deep learning models that enhance CF systems, including Multilayer Perceptrons (MLP), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Graph Neural Networks (GNN), autoencoders, Generative Adversarial Networks (GAN), and Restricted Boltzmann Machines (RBM). The paper also discusses evaluation protocols, various publicly available auxiliary information, and data features. Furthermore, the survey concludes with a discussion of the challenges and future research opportunities in enhancing collaborative filtering systems with deep learning.