Efficient Traffic Prediction Through Spatio-Temporal Distillation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929752226398208 |
|---|---|
| author | Zhang, Qianru Gao, Xinyi Wang, Haixin Yiu, Siu-Ming Yin, Hongzhi |
| author_facet | Zhang, Qianru Gao, Xinyi Wang, Haixin Yiu, Siu-Ming Yin, Hongzhi |
| contents | Graph neural networks (GNNs) have gained considerable attention in recent years for traffic flow prediction due to their ability to learn spatio-temporal pattern representations through a graph-based message-passing framework. Although GNNs have shown great promise in handling traffic datasets, their deployment in real-life applications has been hindered by scalability constraints arising from high-order message passing. Additionally, the over-smoothing problem of GNNs may lead to indistinguishable region representations as the number of layers increases, resulting in performance degradation. To address these challenges, we propose a new knowledge distillation paradigm termed LightST that transfers spatial and temporal knowledge from a high-capacity teacher to a lightweight student. Specifically, we introduce a spatio-temporal knowledge distillation framework that helps student MLPs capture graph-structured global spatio-temporal patterns while alleviating the over-smoothing effect with adaptive knowledge distillation. Extensive experiments verify that LightST significantly speeds up traffic flow predictions by 5X to 40X compared to state-of-the-art spatio-temporal GNNs, all while maintaining superior accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_10459 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Traffic Prediction Through Spatio-Temporal Distillation Zhang, Qianru Gao, Xinyi Wang, Haixin Yiu, Siu-Ming Yin, Hongzhi Machine Learning Computational Engineering, Finance, and Science Graph neural networks (GNNs) have gained considerable attention in recent years for traffic flow prediction due to their ability to learn spatio-temporal pattern representations through a graph-based message-passing framework. Although GNNs have shown great promise in handling traffic datasets, their deployment in real-life applications has been hindered by scalability constraints arising from high-order message passing. Additionally, the over-smoothing problem of GNNs may lead to indistinguishable region representations as the number of layers increases, resulting in performance degradation. To address these challenges, we propose a new knowledge distillation paradigm termed LightST that transfers spatial and temporal knowledge from a high-capacity teacher to a lightweight student. Specifically, we introduce a spatio-temporal knowledge distillation framework that helps student MLPs capture graph-structured global spatio-temporal patterns while alleviating the over-smoothing effect with adaptive knowledge distillation. Extensive experiments verify that LightST significantly speeds up traffic flow predictions by 5X to 40X compared to state-of-the-art spatio-temporal GNNs, all while maintaining superior accuracy. |
| title | Efficient Traffic Prediction Through Spatio-Temporal Distillation |
| topic | Machine Learning Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2501.10459 |