Attention-based dynamic user modeling and Deep Collaborative filtering recommendation

• Published in: Expert systems with applications 2022-02, Vol.188, p.116036, Article 116036
• Main Authors: Wang, Ruiqin, Wu, Zongda, Lou, Jungang, Jiang, Yunliang
• Format: Article
• Language: English
• Subjects: Deep learning; Dynamic preference modeling; Long-term preferences; Matching; Matching score prediction; Mathematical analysis; Modelling; Preferences; Recommender systems; Short-term preferences; Time-aware attention
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2021.116036

•a time-aware attention mechanism to model dynamic user preferences.•a two-stage DL model with representation learning and matching function learning.•a CF model with low-order and high-order feature interaction learning ability. Deep learning (DL) techniques have been widely used in recommender systems for user modeling and matching function learning based on historical interaction matrix. However, existing DL-based recommendation methods usually perform static user preference modeling by using historical interacted items of the user. In this article, we present a time-aware deep CF framework which contains two stages: dynamic user preference modeling based on attention mechanism and matching score prediction based on DL. In the first stage, short-term user preferences are modeled by the time-aware attention mechanism that fully considered the predicted item, the recent interacted items and their interaction time. The resulting short-term preferences are combined with long-term preferences for dynamic user preference modeling. In the second stage, high-order user-item feature interactions are learned by two types of DL models, Deep Matrix Factorization (DMF) and Multiple-Layer Perception (MLP), and the feature interaction vectors of the two models are fused in the last layer of the model to predict the matching score. Extensive experiments on five datasets indicate that our method is superior to the existing time-aware and DL-based recommendation methods in top-k recommendations significantly and consistently.