Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.07314 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914187298471936 |
|---|---|
| author | Luo, Yuxiao Zhang, Songming Ruan, Sijie Chen, Siran Liu, Kang Xu, Yang Zheng, Yu Yin, Ling |
| author_facet | Luo, Yuxiao Zhang, Songming Ruan, Sijie Chen, Siran Liu, Kang Xu, Yang Zheng, Yu Yin, Ling |
| contents | Modeling human mobility is vital for extensive applications such as transportation planning and epidemic modeling. With the rise of the Artificial Intelligence Generated Content (AIGC) paradigm, recent works explore synthetic trajectory generation using autoregressive and diffusion models. While these methods show promise for generating single-day trajectories, they remain limited by inefficiencies in long-term generation (e.g., weekly trajectories) and a lack of explicit spatiotemporal multi-scale modeling. This study proposes Multi-Scale Spatio-Temporal AutoRegression (M-STAR), a new framework that generates long-term trajectories through a coarse-to-fine spatiotemporal prediction process. M-STAR combines a Multi-scale Spatiotemporal Tokenizer that encodes hierarchical mobility patterns with a Transformer-based decoder for next-scale autoregressive prediction. Experiments on two real-world datasets show that M-STAR outperforms existing methods in fidelity and significantly improves generation speed. The data and codes are available at https://github.com/YuxiaoLuo0013/M-STAR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07314 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | M-STAR: Multi-Scale Spatiotemporal Autoregression for Human Mobility Modeling Luo, Yuxiao Zhang, Songming Ruan, Sijie Chen, Siran Liu, Kang Xu, Yang Zheng, Yu Yin, Ling Artificial Intelligence Machine Learning Modeling human mobility is vital for extensive applications such as transportation planning and epidemic modeling. With the rise of the Artificial Intelligence Generated Content (AIGC) paradigm, recent works explore synthetic trajectory generation using autoregressive and diffusion models. While these methods show promise for generating single-day trajectories, they remain limited by inefficiencies in long-term generation (e.g., weekly trajectories) and a lack of explicit spatiotemporal multi-scale modeling. This study proposes Multi-Scale Spatio-Temporal AutoRegression (M-STAR), a new framework that generates long-term trajectories through a coarse-to-fine spatiotemporal prediction process. M-STAR combines a Multi-scale Spatiotemporal Tokenizer that encodes hierarchical mobility patterns with a Transformer-based decoder for next-scale autoregressive prediction. Experiments on two real-world datasets show that M-STAR outperforms existing methods in fidelity and significantly improves generation speed. The data and codes are available at https://github.com/YuxiaoLuo0013/M-STAR. |
| title | M-STAR: Multi-Scale Spatiotemporal Autoregression for Human Mobility Modeling |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2512.07314 |