PreSTNet: Pre-trained Spatio-Temporal Network for traffic forecasting
文献类型：期刊论文
| 作者 | Fang, Shen1 ; Ji, Wei1; Xiang, Shiming2,3; Hua, Wei1
|
| 刊名 | INFORMATION FUSION
 |
| 出版日期 | 2024-06-01 |
| 卷号 | 106页码:13 |
| 关键词 | Traffic forecasting Spatio-temporal graph neural network Pre-training |
| ISSN号 | 1566-2535 |
| DOI | 10.1016/j.inffus.2024.102241 |
| 通讯作者 | Hua, Wei(huawei@zhejianglab.com) |
| 英文摘要 | Traffic forecasting stands as a cornerstone in urban planning, yet existing methods mainly fall short in capturing long-term spatio-temporal patterns. To be specific, various exquisite modules are designed in current works, while bringing heavy computing costs with the length of historical data. Furthermore, any replacement or reintegration of modules could weaken final performance, and the whole model needs to be trained from scratch on different datasets. To address the above shortcomings, inspired by pre -training methodologies, we introduce a novel Pre -trained Spatio-Temporal Network (PreSTNet), a two-phase framework comprising pretraining and fine-tuning. In the first pre -training phase, PreSTNet undertakes a data masking and recovery task, which is facilitated through a dedicated long sequence embedding module and an encoder-decoder structure with temporal attention layers and graph convolution operators. The recovery task involves masking several data, forcing the model to capture correlations between unmasked data and finally recover the masked part, which facilitates the extraction of long-term spatio-temporal features from extensive data. The second phase involves freezing the learned parameters and replacing the decoder with a forecasting header. This header, designed as a meta -learning fusion module and spatio-temporal convolution layers, can integrate long-term and short-term traffic data, and is trained in the manner of supervised learning to suit the target task. Rigorous experiments on real -world datasets underscore the superiority of PreSTNet. Further case studies reveal that the pre -trained encoder, coupled with an intuitive linear regression, achieves comparable performance to advanced methods. These findings affirm the robust capabilities of the proposed PreSTNet in addressing the complexities of traffic forecasting. |
| WOS关键词 | NEURAL-NETWORKS ; DATA FUSION ; PREDICTION |
| 资助项目 | National Natural Science Foundation of China[52232015] ; China Postdoctoral Science Foundation[2023M743259] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001170271600001 |
| 出版者 | ELSEVIER |
| 资助机构 | National Natural Science Foundation of China ; China Postdoctoral Science Foundation |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57815]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
| 通讯作者 | Hua, Wei |
| 作者单位 | 1.Res Ctr Intelligent Transportat, Zhejiang Lab, Hangzhou 311100, Zhejiang, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China |
| 推荐引用方式 GB/T 7714 | Fang, Shen,Ji, Wei,Xiang, Shiming,et al. PreSTNet: Pre-trained Spatio-Temporal Network for traffic forecasting[J]. INFORMATION FUSION,2024,106:13. |
| APA | Fang, Shen,Ji, Wei,Xiang, Shiming,&Hua, Wei.(2024).PreSTNet: Pre-trained Spatio-Temporal Network for traffic forecasting.INFORMATION FUSION,106,13. |
| MLA | Fang, Shen,et al."PreSTNet: Pre-trained Spatio-Temporal Network for traffic forecasting".INFORMATION FUSION 106(2024):13. |
入库方式： OAI收割
来源：自动化研究所
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。