Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912012014977024 |
|---|---|
| author | Dong, Zheng Jiang, Renhe Gao, Haotian Liu, Hangchen Deng, Jinliang Wen, Qingsong Song, Xuan |
| author_facet | Dong, Zheng Jiang, Renhe Gao, Haotian Liu, Hangchen Deng, Jinliang Wen, Qingsong Song, Xuan |
| contents | Spatiotemporal time series forecasting plays a key role in a wide range of real-world applications. While significant progress has been made in this area, fully capturing and leveraging spatiotemporal heterogeneity remains a fundamental challenge. Therefore, we propose a novel Heterogeneity-Informed Meta-Parameter Learning scheme. Specifically, our approach implicitly captures spatiotemporal heterogeneity through learning spatial and temporal embeddings, which can be viewed as a clustering process. Then, a novel spatiotemporal meta-parameter learning paradigm is proposed to learn spatiotemporal-specific parameters from meta-parameter pools, which is informed by the captured heterogeneity. Based on these ideas, we develop a Heterogeneity-Informed Spatiotemporal Meta-Network (HimNet) for spatiotemporal time series forecasting. Extensive experiments on five widely-used benchmarks demonstrate our method achieves state-of-the-art performance while exhibiting superior interpretability. Our code is available at https://github.com/XDZhelheim/HimNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_10800 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting Dong, Zheng Jiang, Renhe Gao, Haotian Liu, Hangchen Deng, Jinliang Wen, Qingsong Song, Xuan Machine Learning Spatiotemporal time series forecasting plays a key role in a wide range of real-world applications. While significant progress has been made in this area, fully capturing and leveraging spatiotemporal heterogeneity remains a fundamental challenge. Therefore, we propose a novel Heterogeneity-Informed Meta-Parameter Learning scheme. Specifically, our approach implicitly captures spatiotemporal heterogeneity through learning spatial and temporal embeddings, which can be viewed as a clustering process. Then, a novel spatiotemporal meta-parameter learning paradigm is proposed to learn spatiotemporal-specific parameters from meta-parameter pools, which is informed by the captured heterogeneity. Based on these ideas, we develop a Heterogeneity-Informed Spatiotemporal Meta-Network (HimNet) for spatiotemporal time series forecasting. Extensive experiments on five widely-used benchmarks demonstrate our method achieves state-of-the-art performance while exhibiting superior interpretability. Our code is available at https://github.com/XDZhelheim/HimNet. |
| title | Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.10800 |