Traj-Transformer: Diffusion Models with Transformer for GPS Trajectory Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Zhiyang, Chen, Ningcong, Zhang, Xin, Li, Yanhua, Su, Shen, Lu, Hui, Luo, Jun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909830749356032
author Zhang, Zhiyang
Chen, Ningcong
Zhang, Xin
Li, Yanhua
Su, Shen
Lu, Hui
Luo, Jun
author_facet Zhang, Zhiyang
Chen, Ningcong
Zhang, Xin
Li, Yanhua
Su, Shen
Lu, Hui
Luo, Jun
contents The widespread use of GPS devices has driven advances in spatiotemporal data mining, enabling machine learning models to simulate human decision making and generate realistic trajectories, addressing both data collection costs and privacy concerns. Recent studies have shown the promise of diffusion models for high-quality trajectory generation. However, most existing methods rely on convolution based architectures (e.g. UNet) to predict noise during the diffusion process, which often results in notable deviations and the loss of fine-grained street-level details due to limited model capacity. In this paper, we propose Trajectory Transformer, a novel model that employs a transformer backbone for both conditional information embedding and noise prediction. We explore two GPS coordinate embedding strategies, location embedding and longitude-latitude embedding, and analyze model performance at different scales. Experiments on two real-world datasets demonstrate that Trajectory Transformer significantly enhances generation quality and effectively alleviates the deviation issues observed in prior approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06291
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Traj-Transformer: Diffusion Models with Transformer for GPS Trajectory Generation
Zhang, Zhiyang
Chen, Ningcong
Zhang, Xin
Li, Yanhua
Su, Shen
Lu, Hui
Luo, Jun
Machine Learning
Artificial Intelligence
The widespread use of GPS devices has driven advances in spatiotemporal data mining, enabling machine learning models to simulate human decision making and generate realistic trajectories, addressing both data collection costs and privacy concerns. Recent studies have shown the promise of diffusion models for high-quality trajectory generation. However, most existing methods rely on convolution based architectures (e.g. UNet) to predict noise during the diffusion process, which often results in notable deviations and the loss of fine-grained street-level details due to limited model capacity. In this paper, we propose Trajectory Transformer, a novel model that employs a transformer backbone for both conditional information embedding and noise prediction. We explore two GPS coordinate embedding strategies, location embedding and longitude-latitude embedding, and analyze model performance at different scales. Experiments on two real-world datasets demonstrate that Trajectory Transformer significantly enhances generation quality and effectively alleviates the deviation issues observed in prior approaches.
title Traj-Transformer: Diffusion Models with Transformer for GPS Trajectory Generation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.06291