A Knowledge-Enhanced Framework for Imitative Transportation Trajectory Generation

Qingyan Zhu, Yize Chen, Hao Wang, Zhenyu Zeng, Hao Liu

Abstract: Designing efficient tools for modeling and analyzing transportation trajectories help improve various smart city services, e.g., location prediction, business recommendation and traffic forecasting. Yet with limited historical travel data, conventional tools are faced with challenges in representing the sophisticated contextual and spatiotemporal relationships inherent in transportation trajectories, while such trajectories have strong functional, geographical and time-specific characteristics. In this work, we propose an imitative transportation trajectory generation framework with multi-source urban knowledge enhancement. Specifically, we first construct Know-ST, an urban knowledge fusion framework that captures cross-domain knowledge (i.e., road network, point of interest, etc.) via tailored urban knowledge graph representation learning. The Know-ST preserves the temporal characteristics of trajectories and can continuously adapt to newly arriving trajectories. Moreover, we formulate the trajectory generation problem as a sequential imitation learning process, where an adversarially trained generator network is equipped to autonomously capture both the spatiotemporal and contextual information within individual transportation trajectories. Extensive experiments on real-world dataset show Know-ST outperforms multiple baselines under a variety of benchmarks, indicating the effectiveness of the proposed framework.