ST-LoRA: Low-Rank Adaptation for Spatio-Temporal Forecasting
文献类型：期刊论文
| 作者 | Ruan, Weilin3; Chen, Wei3; Dang, Xilin2; Zhou, Jianxiang3; Li, Weichuang3; Liu, Xu1; Liang, Yuxuan3,4 |
| 刊名 | MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES. RESEARCH TRACK, ECML PKDD 2025, PT VII
 |
| 出版日期 | 2026 |
| 卷号 | 16019页码:345-361 |
| ISSN号 | 2945-9133 |
| DOI | 10.1007/978-3-032-06109-6_20 |
| 产权排序 | 4 |
| 文献子类 | Proceedings Paper |
| 英文摘要 | Spatio-temporal forecasting is essential for understanding future dynamics within real-world systems by leveraging historical data from multiple locations. Existing methods often prioritize the development of intricate neural networks to capture the complex dependencies of the data. These methods neglect node-level heterogeneity and face over-parameterization when attempting to model node-specific characteristics. In this paper, we present a novel low-rank adaptation framework for existing Datio-temporal prediction models, termed ST-LoRA, which alleviates the aforementioned problems through node-level adjustments. Specifically, we introduce the node-adaptive low-rank layer and node-specific predictor, capturing the complex functional characteristics of nodes while maintaining computational efficiency. Extensive experiments on multiple real-world datasets demonstrate that our method consistently achieves superior performance across various forecasting models with minimal computational overhead, improving performance by 7% with only 1% additional parameter cost. The source code is available at https://github.com/RWLinno/ST-LoRA. |
| URL标识 | 查看原文 |
| WOS关键词 | TRAFFIC FLOW ; NETWORK |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001677401500020 |
| 出版者 | SPRINGER INTERNATIONAL PUBLISHING AG |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221362]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Liang, Yuxuan |
| 作者单位 | 1.Natl Univ Singapore, Singapore, Singapore; 2.Chinese Univ Hong Kong, Sha Tin, Hong Kong, Peoples R China; 3.Hong Kong Univ Sci & Technol Guangzhou, Guangzhou, Peoples R China; 4.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Ruan, Weilin,Chen, Wei,Dang, Xilin,et al. ST-LoRA: Low-Rank Adaptation for Spatio-Temporal Forecasting[J]. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES. RESEARCH TRACK, ECML PKDD 2025, PT VII,2026,16019:345-361. |
| APA | Ruan, Weilin.,Chen, Wei.,Dang, Xilin.,Zhou, Jianxiang.,Li, Weichuang.,...&Liang, Yuxuan.(2026).ST-LoRA: Low-Rank Adaptation for Spatio-Temporal Forecasting.MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES. RESEARCH TRACK, ECML PKDD 2025, PT VII,16019,345-361. |
| MLA | Ruan, Weilin,et al."ST-LoRA: Low-Rank Adaptation for Spatio-Temporal Forecasting".MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES. RESEARCH TRACK, ECML PKDD 2025, PT VII 16019(2026):345-361. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。