A unified hierarchical attention framework for sequential recommendation by fusing long and short-term preferences. (1st September 2022)

• Record Type: Journal Article
• Authors: Du, Yongping; Peng, Zhi; Niu, Jinyu; Yan, Jingya
• Is Part Of: Expert systems with applications. Volume 201(2022)
• Publication Date: 2022-09-01
• Subjects: Behavior sequences -- Feature interactions -- Hierarchical attention -- Long and short-term preferences -- Sequential recommendation; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.117102
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Sequential recommendation becomes a critical task in many application scenarios, since people's online activities are increasing. In order to predict the next item that users may be interested, it is necessary to take both general and dynamic preferences of the user into account. Existing approaches typically integrate the user–item or item–item feature interactions directly without considering the dynamic changes of the user's long-term and short-term preferences, which also limits the capability of the model. To address these issues, we propose a novel unified framework for sequential recommendation task, modeling users' long and short-term sequential behaviors at each time step and capturing item-to-item dependencies in higher-order by hierarchical attention mechanism. The proposed model considers the dynamic long and short-term user preferences simultaneously, and a joint learning mechanism is introduced to fuse them for better recommendation. We extensively evaluate our model with several state-of-the-art methods by different validation metrics on three real-world datasets. The experimental results demonstrate the significant improvement of our approach over other compared models. Highlights: A novel unified framework for sequential recommendation is proposed. Multi-head self-attention captures both the general and dynamic user preferences. Hierarchical attention obtains the item–item interaction features in higher order. A joint learning mechanism fuses the long and short-term features effectively. The proposed model achieves significant improvement over other related method.