A Deep Latent Factor Model for High-Dimensional and Sparse Matrices in Recommender Systems

Recommender systems (RSs) commonly adopt a user-item rating matrix to describe users' preferences on items. With users and items exploding, such a matrix is usually high-dimensional and sparse (HiDS). Recently, the idea of deep learning has been applied to RSs. However, current deep-structured RSs suffer from high computational complexity. Enlightened by the idea of deep forest, this paper proposes a deep latent factor model (DLFM) for building a deep-structured RS on an HiDS matrix efficiently. Its main idea is to construct a deep-structured model by sequentially connecting multiple latent factor (LF) models instead of multilayered neural networks through a nonlinear activation function. Thus, the computational complexity grows linearly with its layer count, which is easy to resolve in practice. The experimental results on four HiDS matrices from industrial RSs demonstrate that when compared with state-of-the-art LF models and deep-structured RSs, DLFM can well balance the prediction accuracy and computational efficiency, which well fits the desire of industrial RSs for fast and right recommendations.

Automated summary

The paper proposes a deep latent factor model (DLFM) for building a deep-structured RS efficiently on a high-dimensional and sparse matrix, by sequentially connecting multiple latent factor models to construct a deep-structured model. The experimental results show that DLFM can balance prediction accuracy and computational efficiency better than state-of-the-art models, meeting the industrial RS's need for fast and accurate recommendations.