Efficient Neural Matrix Factorization without Sampling for Recommendation

TLDR

Recommendation systems keep users engaged, and while deep learning has spurred interest, current methods rely on complex architectures and negative sampling, which lead to many parameters, high computation costs, and robustness issues. This study proposes learning neural recommendation models from the entire training data without sampling. To enable efficient non‑sampling learning, we derive three low‑complexity optimization methods and introduce the ENMF framework built on a simple neural matrix factorization architecture. Experiments on three public datasets show ENMF consistently outperforms state‑of‑the‑art methods on Top‑K recommendation and achieves markedly faster training, making it suitable for large‑scale systems.

Abstract

Recommendation systems play a vital role to keep users engaged with personalized contents in modern online platforms. Recently, deep learning has revolutionized many research fields and there is a surge of interest in applying it for recommendation. However, existing studies have largely focused on exploring complex deep-learning architectures for recommendation task, while typically applying the negative sampling strategy for model learning. Despite effectiveness, we argue that these methods suffer from two important limitations: (1) the methods with complex network structures have a substantial number of parameters, and require expensive computations even with a sampling-based learning strategy; (2) the negative sampling strategy is not robust, making sampling-based methods difficult to achieve the optimal performance in practical applications. In this work, we propose to learn neural recommendation models from the whole training data without sampling. However, such a non-sampling strategy poses strong challenges to learning efficiency. To address this, we derive three new optimization methods through rigorous mathematical reasoning, which can efficiently learn model parameters from the whole data (including all missing data) with a rather low time complexity. Moreover, based on a simple Neural Matrix Factorization architecture, we present a general framework named ENMF, short for Efficient Neural Matrix Factorization . Extensive experiments on three real-world public datasets indicate that the proposed ENMF framework consistently and significantly outperforms the state-of-the-art methods on the Top-K recommendation task. Remarkably, ENMF also shows significant advantages in training efficiency, which makes it more applicable to real-world large-scale systems.