Guardado en:
Detalles Bibliográficos
Autores principales: Luo, Kang, Zhu, Yuanshao, Chen, Wei, Wang, Kun, Zhou, Zhengyang, Ruan, Sijie, Liang, Yuxuan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2404.14073
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911848602796032
author Luo, Kang
Zhu, Yuanshao
Chen, Wei
Wang, Kun
Zhou, Zhengyang
Ruan, Sijie
Liang, Yuxuan
author_facet Luo, Kang
Zhu, Yuanshao
Chen, Wei
Wang, Kun
Zhou, Zhengyang
Ruan, Sijie
Liang, Yuxuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_14073
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning
Luo, Kang
Zhu, Yuanshao
Chen, Wei
Wang, Kun
Zhou, Zhengyang
Ruan, Sijie
Liang, Yuxuan
Machine Learning
Artificial Intelligence
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.
title Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2404.14073