Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning

Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning

Kang Luo, Yuanshao Zhu, Wei Chen, Kun Wang, Zhengyang Zhou, Sijie Ruan, Yuxuan Liang

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Main Track. Pages 2243-2251. https://doi.org/10.24963/ijcai.2024/248

Trajectory modeling refers to characterizing human movement behavior, serving as a pivotal step in understanding mobility patterns. Nevertheless, existing studies typically ignore the confounding effects of geospatial context, leading to the acquisition of spurious correlations and limited generalization capabilities. To bridge this gap, we initially formulate a Structural Causal Model (SCM) to decipher the trajectory representation learning process from a causal perspective. Building upon the SCM, we further present a Trajectory modeling framework (TrajCL) based on Causal Learning, which leverages the backdoor adjustment theory as an intervention tool to eliminate the spurious correlations between geospatial context and trajectories. Extensive experiments on two real-world datasets verify that TrajCL markedly enhances performance in trajectory classification tasks while showcasing superior generalization and interpretability.
Keywords:
Data Mining: DM: Mining spatial and/or temporal data
Multidisciplinary Topics and Applications: MTA: Transportation