Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting

doi:10.14778/3551793.3551827

	Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting
	Shao, Zezhi 1,2; Zhang, Zhao 1; Wei, Wei 3; Wang, Fei 1; Xu, Yongjun 1; Cao, Xin 4; Jensen, Christian S.5
	2022-07-01
发表期刊	PROCEEDINGS OF THE VLDB ENDOWMENT
ISSN	2150-8097
卷号	15 期号:11 页码:2733-2746
摘要	We all depend on mobility, and vehicular transportation affects the daily lives of most of us. Thus, the ability to forecast the state of traffic in a road network is an important functionality and a challenging task. Traffic data is often obtained from sensors deployed in a road network. Recent proposals on spatial-temporal graph neural networks have achieved great progress at modeling complex spatial-temporal correlations in traffic data, by modeling traffic data as a diffusion process. However, intuitively, traffic data encompasses two different kinds of hidden time series signals, namely the diffusion signals and inherent signals. Unfortunately, nearly all previous works coarsely consider traffic signals entirely as the outcome of the diffusion, while neglecting the inherent signals, which impacts model performance negatively. To improve modeling performance, we propose a novel Decoupled Spatial-Temporal Framework (DSTF) that separates the diffusion and inherent traffic information in a data-driven manner, which encompasses a unique estimation gate and a residual decomposition mechanism. The separated signals can be handled subsequently by the diffusion and inherent modules separately. Further, we propose an instantiation of DSTF, Decoupled Dynamic Spatial-Temporal Graph Neural Network (D(2)STGNN), that captures spatial-temporal correlations and also features a dynamic graph learning module that targets the learning of the dynamic characteristics of traffic networks. Extensive experiments with four real-world traffic datasets demonstrate that the framework is capable of advancing the state-of-the-art.
DOI	10.14778/3551793.3551827
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61902376] ; National Natural Science Foundation of China[61902382] ; National Natural Science Foundation of China[61602197] ; CCF-AFSG Research Fund[RF20210005] ; HUST ; Pingan Property & Casualty Research (HPL) ; China Postdoctoral Science Foundation[2021M703273]
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Theory & Methods
WOS记录号	WOS:000992390600035
出版者	ASSOC COMPUTING MACHINERY
引用统计	被引频次：26[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21424
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wei, Wei; Wang, Fei
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Wuhan, Peoples R China 4.Univ New South Wales, Sch Comp Sci & Engn, Sydney, NSW, Australia 5.Aalborg Univ, Dept Comp Sci, Aalborg, Denmark
推荐引用方式 GB/T 7714	Shao, Zezhi,Zhang, Zhao,Wei, Wei,et al. Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting[J]. PROCEEDINGS OF THE VLDB ENDOWMENT,2022,15(11):2733-2746.
APA	Shao, Zezhi.,Zhang, Zhao.,Wei, Wei.,Wang, Fei.,Xu, Yongjun.,...&Jensen, Christian S..(2022).Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting.PROCEEDINGS OF THE VLDB ENDOWMENT,15(11),2733-2746.
MLA	Shao, Zezhi,et al."Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting".PROCEEDINGS OF THE VLDB ENDOWMENT 15.11(2022):2733-2746.