DLAN:Modeling user long- and short-term preferences based on double-layer attention network for next point-of-interest recommendation

Article type: Research Article

Authors: Wu, Yuhang^{a; b} | Jiao, Xu^{c; d} | Hao, Qingbo^{a; b} | Xiao, Yingyuan^{a; b; *} | Zheng, Wenguang^{a; b; *}

Affiliations: [a] Engineering Research Center of Learning-Based Intelligent System, Ministry of Education, Tianjin, China | [b] Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin, China | [c] School of General Education, Tianjin Foreign Studies University, Tianjin, China | [d] Department of Computer Science, Norwegian University of Science and Technology, Norway

Correspondence: [*] Corresponding author. Yingyuan Xiao and Wenguang Zheng. E-mails: yyxiao@tjut.edu.cn; wenguangz@tjut.edu.cn.

Abstract: The next Point-of-Interest (POI) recommendation, in recent years, has attracted an extensive amount of attention from the academic community. RNN-based methods cannot establish effective long-term dependencies among the input sequences when capturing the user’s motion patterns, resulting in inadequate exploitation of user preferences. Besides, the majority of prior studies often neglect high-order neighborhood information in users’ check-in trajectory and their social relationships, yielding suboptimal recommendation efficacy. To address these issues, this paper proposes a novel Double-Layer Attention Network model, named DLAN. Firstly, DLAN incorporates a multi-head attention module that can combine first-order and high-order neighborhood information in user check-in trajectories, thereby effectively and parallelly capturing both long- and short-term preferences of users and overcoming the problem that RNN-based methods cannot establish long-term dependencies between sequences. Secondly, this paper designs a user similarity weighting layer to measure the influence of other users on the target users leverage the social relationships among them. Finally, comprehensive experiments are conducted on user check-in data from two cities, New York (NYC) and Tokyo (TKY), and the results demonstrate that DLAN achieves a performance in Accuracy and Mean Reverse Rank enhancement by 8.07% -36.67% compared to the state-of-the-art method. Moreover, to investigate the effect of dimensionality and the number of heads of the multi-head attention mechanism on the performance of the DLAN model, we have done sufficient sensitivity experiments.

Keywords: Point-of-interest recommendation, user preferences, attention network, social information

DOI: 10.3233/JIFS-232491

Journal: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 2, pp. 3307-3321, 2024