Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning

Autor:	Luo, Kang, Zhu, Yuanshao, Chen, Wei, Wang, Kun, Zhou, Zhengyang, Ruan, Sijie, Liang, Yuxuan
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	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. Comment: The paper has been accepted by IJCAI 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2404.14073 Zobrazit plný text záznamu View this record from Arxiv