Is Simple Better? Revisiting Non-linear Matrix Factorization for Learning Incomplete Ratings

TL;DR

This paper introduces a multilayer nonlinear semi-nonnegative matrix factorization method for collaborative filtering, demonstrating improved prediction accuracy and comparable clustering performance compared to deep learning approaches.

Contribution

It proposes a novel multilayer nonlinear semi-NMF approach that models user-item interactions more accurately using non-linear item features, outperforming existing deep matrix factorization methods.

Findings

Achieves better generalization in rating prediction.

Provides comparable clustering performance to deep matrix factorization.

Outperforms classical methods in modeling user-item interactions.

Abstract

Matrix factorization techniques have been widely used as a method for collaborative filtering for recommender systems. In recent times, different variants of deep learning algorithms have been explored in this setting to improve the task of making a personalized recommendation with user-item interaction data. The idea that the mapping between the latent user or item factors and the original features is highly nonlinear suggest that classical matrix factorization techniques are no longer sufficient. In this paper, we propose a multilayer nonlinear semi-nonnegative matrix factorization method, with the motivation that user-item interactions can be modeled more accurately using a linear combination of non-linear item features. Firstly, we learn latent factors for representations of users and items from the designed multilayer nonlinear Semi-NMF approach using explicit ratings. Secondly, the architecture built is compared with deep-learning algorithms like Restricted Boltzmann Machine and state-of-the-art Deep Matrix factorization techniques. By using both supervised rate prediction task and unsupervised clustering in latent item space, we demonstrate that our proposed approach achieves better generalization ability in prediction as well as comparable representation ability as deep matrix factorization in the clustering task.