It is becoming a hot research topic to predict where a user would visit in a neighboring city based on check-in data collected from location-based mobile Apps. However, as most users rarely travel out of hometown, there is a high skew of the quantity of check-in data between hometown and neighboring cities. Suffering from the severe sparsity of user mobility data, existing studies do not perform well as they can hardly maintain users' intrinsic preference and meanwhile adapt to their interest drift. To address these concerns, in this work, we propose a novel framework called TIOMP, where a user-specific travel intention is formulated as an aggregation combining his/her hometown preference and the generic travel intention out-of-town, which is distilled by the distance dependent Chinese Restaurant Process (ddCRP) and the intention-enhanced memory network. Besides, we propose to portray POIs through GNN incorporating POI attributes and geographical information. Finally, the user and POI representations are combined for prediction. Extensive experiments on real-world datasets validate the superiority of our framework over several state-of-the-art approaches.
Shuai Xu received the bachelor’s degree in computer science from Northeastern University, China, in 2014, and the Ph.D. degree in computer science from Southeast University, China, in 2020. He is currently a lecturer at the College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, China. From 2018 to 2020, he visited the University of Göttingen, Germany, where he was a research assistant, hosted by Prof. Xiaoming Fu. He has authored nearly 20 articles and most of them have been published in reputed journals and conferences, including IEEE TCSS, WWWJ, JNCA, CIKM, and DASFAA. He won the ACM Excellent Doctoral Dissertation Award (Nanjing Branch) in 2021, and the Best Student Paper Award in APWeb-WAIM 2022. His current research interests include temporal-spatial data mining and social network analysis.