A Recommender System Based on Model Regularization Wasserstein Generative Adversarial Network

A recommender system (RS) commonly adopts a High-dimensional and sparse (HiDS) matrix to describe user-item preferences. Collaborative Filtering (CF)-based models have been widely adopted to address such an HiDS matrix. However, a CF-based model is unable to learn the property distribution characteristic of user’s preference from an HiDS matrix, thereby its representation ability is limited. To address this issue, this paper proposes a Model Regularization Wasserstein GAN(MRWGAN) to extract the distribution of user’s preferences. Its main ideas are two-fold: a) adopting an auto-encoder to implement the generator model of GAN; b) proposing a model-regularized Wasserstein distance as an objective function to training a GAN model. Empirical studies on four HiDS matrices from industrial applications demonstrate that compared with state-of-the-art models, the proposed model achieves higher prediction accuracy for missing data of an HiDS matrix.

I. Introduction

The rapid expansion of the world-wide-web has caused the problem of information overload. It is hard for people to filter out the desired information from billions of data. In such context, recommender systems (RSs) have attracted great interest since they can perform efficient information filtering [1].