Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.23048 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918037661155328 |
|---|---|
| author | Bu, Tianci Zhou, Le Yang, Wenchuan Mou, Jianhong Yang, Kang Tan, Suoyi Yao, Feng Wang, Jingyuan Lu, Xin |
| author_facet | Bu, Tianci Zhou, Le Yang, Wenchuan Mou, Jianhong Yang, Kang Tan, Suoyi Yao, Feng Wang, Jingyuan Lu, Xin |
| contents | Trajectory data is crucial for various applications but often suffers from incompleteness due to device limitations and diverse collection scenarios. Existing imputation methods rely on sparse trajectory or travel information, such as velocity, to infer missing points. However, these approaches assume that sparse trajectories retain essential behavioral patterns, which place significant demands on data acquisition and overlook the potential of large-scale human trajectory embeddings. To address this, we propose ProDiff, a trajectory imputation framework that uses only two endpoints as minimal information. It integrates prototype learning to embed human movement patterns and a denoising diffusion probabilistic model for robust spatiotemporal reconstruction. Joint training with a tailored loss function ensures effective imputation. ProDiff outperforms state-of-the-art methods, improving accuracy by 6.28\% on FourSquare and 2.52\% on WuXi. Further analysis shows a 0.927 correlation between generated and real trajectories, demonstrating the effectiveness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23048 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation Bu, Tianci Zhou, Le Yang, Wenchuan Mou, Jianhong Yang, Kang Tan, Suoyi Yao, Feng Wang, Jingyuan Lu, Xin Machine Learning Trajectory data is crucial for various applications but often suffers from incompleteness due to device limitations and diverse collection scenarios. Existing imputation methods rely on sparse trajectory or travel information, such as velocity, to infer missing points. However, these approaches assume that sparse trajectories retain essential behavioral patterns, which place significant demands on data acquisition and overlook the potential of large-scale human trajectory embeddings. To address this, we propose ProDiff, a trajectory imputation framework that uses only two endpoints as minimal information. It integrates prototype learning to embed human movement patterns and a denoising diffusion probabilistic model for robust spatiotemporal reconstruction. Joint training with a tailored loss function ensures effective imputation. ProDiff outperforms state-of-the-art methods, improving accuracy by 6.28\% on FourSquare and 2.52\% on WuXi. Further analysis shows a 0.927 correlation between generated and real trajectories, demonstrating the effectiveness of our approach. |
| title | ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.23048 |