STWave<SUP>+</SUP>: A Multi-Scale Efficient Spectral Graph Attention Network With Long-Term Trends for Disentangled Traffic Flow Forecasting

doi:10.1109/TKDE.2023.3324501

	STWave⁺: A Multi-Scale Efficient Spectral Graph Attention Network With Long-Term Trends for Disentangled Traffic Flow Forecasting
	Fang, Yuchen 1; Qin, Yanjun 2; Luo, Haiyong 3; Zhao, Fang 4; Zheng, Kai 1
	2024-06-01
发表期刊	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
ISSN	1041-4347
卷号	36 期号:6 页码:2671-2685
摘要	Traffic forecasting is crucial for public safety and resource optimization, yet is very challenging due to the temporal changes and the dynamic spatial correlations. To capture these intricate dependencies, spatio-temporal networks, such as recurrent neural networks with graph convolution networks, are applied. However, traffic forecasting is still a non-trivial task because of three major challenges: 1) Previous spatio-temporal networks are based on end-to-end training and thus fail to handle the distribution shift in the non-stationary traffic time series. 2) Existing methods always utilize the one-hour input to forecast future traffic and the long-term historical trend knowledge is ignored. 3) The efficient and effective algorithm for modeling multi-scale spatial correlations is still lacking in prior networks. Therefore, in this paper, rather than proposing yet another end-to-end model, we provide a novel disentangle-fusion framework STWave(+) to mitigate the distribution shift issue. The framework first decouples the complex one-hour traffic data into stable trends and fluctuating events, followed by a dual-channel spatio-temporal network to model trends and events, respectively. Moreover, long-term trends are used as a self-supervised signal in STWave(+) to teach overall temporal information into one-hour trends through a contrastive loss. Finally, reasonable future traffic can be predicted through the adaptive fusion of one-hour trends and events. Additionally, we incorporate a novel query sampling strategy and multi-scale graph wavelet positional encoding into the full graph attention network to efficiently and effectively model dynamic hierarchical spatial correlations. Extensive experiments on four traffic datasets show the superiority of our approach, i.e., the higher forecasting accuracy with lower computational cost.
关键词	Market research Forecasting Roads Time series analysis Sensors Correlation Encoding Contrastive learning graph attention network spatio-temporal data traffic forecasting
DOI	10.1109/TKDE.2023.3324501
收录类别	SCI
语种	英语
资助项目	NSFC
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号	WOS:001245459400009
出版者	IEEE COMPUTER SOC
引用统计	被引频次：7[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/2XEOYT63/39921
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zheng, Kai
作者单位	1.Univ Elect Sci & Technol China, Yangtze Delta Reg Inst Quzhou, Sch Comp Sci & Engn, Shenzhen Inst Adv Study, Chengdu 610056, Peoples R China 2.Tsinghua Univ, Dept Elect Engn, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100045, Peoples R China 4.Beijing Univ Posts & Telecommun, Sch Comp Sci, Natl Pilot Software Engn Sch, Beijing 100876, Peoples R China
推荐引用方式 GB/T 7714	Fang, Yuchen,Qin, Yanjun,Luo, Haiyong,et al. STWave⁺: A Multi-Scale Efficient Spectral Graph Attention Network With Long-Term Trends for Disentangled Traffic Flow Forecasting[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2024,36(6):2671-2685.
APA	Fang, Yuchen,Qin, Yanjun,Luo, Haiyong,Zhao, Fang,&Zheng, Kai.(2024).STWave⁺: A Multi-Scale Efficient Spectral Graph Attention Network With Long-Term Trends for Disentangled Traffic Flow Forecasting.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,36(6),2671-2685.
MLA	Fang, Yuchen,et al."STWave⁺: A Multi-Scale Efficient Spectral Graph Attention Network With Long-Term Trends for Disentangled Traffic Flow Forecasting".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 36.6(2024):2671-2685.