When Multitask Learning Make a Difference: Spatio-Temporal Joint Prediction for Cellular Trajectories

• Published in: Database Systems for Advanced Applications Vol. 13245; pp. 207 - 223
• Main Authors: Xu, Yuan, Xu, Jiajie, Fang, Junhua, Liu, An, Zhao, Lei
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2022; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Cellular trajectory; Multitask learning; Spatio-temporal joint prediction
• ISBN: 9783031001222; 3031001222
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-031-00123-9_16

Spatio-temporal joint prediction aims to simultaneously predict the next location and the corresponding switch time for a cellular trajectory. It requires to consider not only the mutual influence of spatio-temporal predicting tasks, but also the signals related to the intentions of the travel. Although multitask learning can support the joint prediction by considering both spatio-temporal signals, existing approaches neglect the effects of travel intentions and fail to model the long-term dependencies in trajectory, resulting in sub-optimal results accordingly. To solve these issues, we propose an intention-aware multitask learning method for spatio-temporal joint prediction, such that predicting travel intention is learned as an auxiliary task. Specifically, due to the implicity of travel intention, we design an effective loss function to learn meaningful intention representation, which can capture trajectory’s future moving goal, so as to provide long-term information for spatio-temporal joint prediction. Furthermore, we carefully design a gating mechanism to fuse sequential and intentional information with different weights to reflect their importance in capturing current movement status. Besides, self-attention network is adopted to model the long-term dependencies of far sampling points in a dense trajectory. Finally, extensive experiments on two trajectory datasets demonstrate the superiority of our method.