DeepAssociate: A deep learning model exploring sequential influence and history-candidate association for sequence recommendation. (15th December 2021)

• Record Type: Journal Article
• Authors: Ma, Yingxue; Gan, Mingxin
• Is Part Of: Expert systems with applications. Volume 185(2021)
• Publication Date: 2021-12-15
• Subjects: Sequential recommendation -- User preference -- Deep learning -- Attention mechanism -- Recurrent neural network; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.115587
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: History-candidate association extraction benefits preference modeling. Integrating history-candidate association in recommendation improves performance. Adopting auxiliary training in sequential recommendation reduces model complexity. Weighted objective function accelerates model convergence. Incorporating training loss from preference modeling enhances model performance. Abstract: A remarkable progress in sequential recommendation field lies on deep learning techniques, where deep learning was widely used to capture user preference from behavior records. However, researchers usually place emphasis on sequential change while ignore the correlation between user's historical behaviors and candidate item's characteristics (history-candidate association), which leads to the inaccurate matching between target users and candidate items. In this paper, we proposed a deep learning model to explore both sequential influence and history-candidate association in sequential recommendation, namely DeepAssociate. First, we considered the history-candidate association in user preference representation and obtained it by two steps, including sequential influence extraction and association feature extraction. Then, by defining a weighted objective function, we introduced an integrated framework which makes a combination of sequential and association features extraction and prediction module to enhance recommendation performance. Experimental results on four real-world datasets demonstrated that DeepAssociate model outperformed state-of-the-art methods on recommendation performance. Furthermore, a series of extensive experiments indicated the benefit of utilizing history-candidate association feature in reducing model complexity and accelerating model convergence.