HUTFormer: Hierarchical U-Net transformer for long-term traffic forecasting

doi:10.1016/j.commtr.2025.100218

CSpace

	HUTFormer: Hierarchical U-Net transformer for long-term traffic forecasting
	Shao, Zezhi 1; Wang, Fei 1,2; Sun, Tao 1; Yu, Chengqing 1,2; Fang, Yuchen 3; Jin, Guangyin 4; An, Zhulin 1; Liu, Yang 5; Qu, Xiaobo 5; Xu, Yongjun 1,2
	2025-12-01
发表期刊	COMMUNICATIONS IN TRANSPORTATION RESEARCH
ISSN	2772-4247
卷号	5 页码:15
摘要	Traffic forecasting, which aims to predict traffic conditions based on historical observations, has been an enduring research topic and is widely recognized as an essential component of intelligent transportation. Recent proposals on Spatial-Temporal Graph Neural Networks (STGNNs) have made significant progress by combining sequential models with graph convolution networks. However, due to high complexity issues, STGNNs only focus on short-term traffic forecasting (e.g., 1-h ahead), while ignoring more practical long-term forecasting. In this paper, we make the first attempt to explore long-term traffic forecasting (e.g., 1-day ahead). To this end, we first reveal its unique challenges in exploiting multi-scale representations. Then, we propose a novel Hierarchical Unet TransFormer (HUTFormer) to address the issues of long-term traffic forecasting. HUTFormer consists of a hierarchical encoder and decoder to jointly generate and utilize multi-scale representations of traffic data. Specifically, for the encoder, we propose window self-attention and segment merging to extract multi-scale representations from long-term traffic data. For the decoder, we design a cross-scale attention mechanism to effectively incorporate multi-scale representations. In addition, HUTFormer employs an efficient input embedding strategy to address the complexity issues. Extensive experiments on four traffic datasets show that the proposed HUTFormer significantly outperforms state-of-the-art traffic forecasting and long time series forecasting baselines.
关键词	Traffic condition forecasting Long-term time series forecasting Multivariate time series forecasting
DOI	10.1016/j.commtr.2025.100218
收录类别	SCI
语种	英语
WOS研究方向	Transportation
WOS类目	Transportation ; Transportation Science & Technology
WOS记录号	WOS:001619741900001
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/43070
专题	中国科学院计算技术研究所
通讯作者	Wang, Fei
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 3.Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 610054, Peoples R China 4.Sapienza Univ Rome, Dept Planning Design & Technol Architecture, I-00196 Rome, Italy 5.Tsinghua Univ, Sch Vehicle & Mobil, Beijing 100084, Peoples R China
推荐引用方式 GB/T 7714	Shao, Zezhi,Wang, Fei,Sun, Tao,et al. HUTFormer: Hierarchical U-Net transformer for long-term traffic forecasting[J]. COMMUNICATIONS IN TRANSPORTATION RESEARCH,2025,5:15.
APA	Shao, Zezhi.,Wang, Fei.,Sun, Tao.,Yu, Chengqing.,Fang, Yuchen.,...&Xu, Yongjun.(2025).HUTFormer: Hierarchical U-Net transformer for long-term traffic forecasting.COMMUNICATIONS IN TRANSPORTATION RESEARCH,5,15.
MLA	Shao, Zezhi,et al."HUTFormer: Hierarchical U-Net transformer for long-term traffic forecasting".COMMUNICATIONS IN TRANSPORTATION RESEARCH 5(2025):15.