AutoMSNet: Multi-Source Spatio-Temporal Network via Automatic Neural Architecture Search for Traffic Flow Prediction

doi:10.1109/TITS.2022.3225553

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	AutoMSNet: Multi-Source Spatio-Temporal Network via Automatic Neural Architecture Search for Traffic Flow Prediction
	Fang, Shen1,2 ; Zhang, Chunxia 2,3; Xiang, Shiming1 ; Pan, Chunhong1
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN	1524-9050
	2022-12-16
页码	15
通讯作者	Xiang, Shiming(smxiang@nlpr.ia.ac.cn)
摘要	Recently the research of traffic flow prediction with deep learning framework has be largely developed, whereas most current methods are still faced with the following shortcomings. For spatial feature extraction, studies have shown that both local and non-local correlations exist on traffic networks. Considering the temporal dependencies, short-term impending and longer periodic components are two most critical patterns of traffic data, which further provide different information for the prediction task. Furthermore, multi-source heterogeneous external data, which naturally holds semantic gap with traffic data, also have impact on traffic flow. To solve the above problems, this paper proposes an AutoMSNet (Multi-Source Spatio-Temporal Network via Automatic neural architecture search). The AutoMSNet is composed of an encoder-decoder structure. The encoder takes neighboring data as inputs, while the decoder captures long-term periodic patterns. Thus, different functions of two temporal features are simultaneously extracted. Moreover, a neural architecture search space is designed for spatial feature extraction. Through architecture search technique, graph convolutions with different receptive fields are automatically selected and combined to form an optimal module structure. Therefore, both local and non-local spatial features can be adaptively captured. Besides, a meta learning feature fusion strategy is proposed to integrate external data, which can alleviate the semantic gap between different data sources. Extensive experiments on three real-world traffic datasets evaluate the superiority of the proposed model.
关键词	Deep learning neural architecture search graph convolution meta-learning traffic flow prediction
DOI	10.1109/TITS.2022.3225553
关键词[WOS]	KALMAN FILTER ; DEEP
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018AAA0100400] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[62072039] ; National Natural Science Foundation of China[62076242]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:000903350700001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：4[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/51022
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
通讯作者	Xiang, Shiming
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 3.Beijing Inst Technol, Sch Comp Sci & Technol, Beijing 100081, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Fang, Shen,Zhang, Chunxia,Xiang, Shiming,et al. AutoMSNet: Multi-Source Spatio-Temporal Network via Automatic Neural Architecture Search for Traffic Flow Prediction[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022:15.
APA	Fang, Shen,Zhang, Chunxia,Xiang, Shiming,&Pan, Chunhong.(2022).AutoMSNet: Multi-Source Spatio-Temporal Network via Automatic Neural Architecture Search for Traffic Flow Prediction.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,15.
MLA	Fang, Shen,et al."AutoMSNet: Multi-Source Spatio-Temporal Network via Automatic Neural Architecture Search for Traffic Flow Prediction".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022):15.