STHAN: Transportation Demand Forecasting with Compound Spatio-Temporal Relationships

doi:doi.org/10.1145/3565578

	STHAN: Transportation Demand Forecasting with Compound Spatio-Temporal Relationships
	Ling, Shuai1 ; Yu, Zhe 2; Cao, Shaosheng 2; Zhang, Haipeng1 ; Hu, Simon 3
	2023-02
发表期刊	ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA (IF:4.0[JCR-2023],3.9[5-Year])
ISSN	1556-4681
EISSN	1556-472X
卷号	17 期号:4
发表状态	已发表
DOI	doi.org/10.1145/3565578
摘要	Transportation demand forecasting is a critical precondition of optimal online transportation dispatch, which will greatly reduce drivers' wasted mileage and customers' waiting time, contributing to economic and environmental sustainability. Though variousmethods have been developed, the core spatio-temporal complexity remains challenging from three perspectives: (1) Compound spatial relationships. According to our empirical analysis, these relationships widely exist. Previous studies focus on capturing different spatial relationships using multi-homogeneous graphs. However, the information flow across various spatial relationships is not modeled explicitly. (2) Heterogeneity in spatial relationships. A region's neighbors under the same spatial relationship may have different weights for this region. Meanwhile, different relationships may also weigh differently. (3) Synchronicity between compound spatial relationships and temporal relationships. Previous research considers synchronous influences from spatial and temporal relationships in a homogeneous fashion while compound spatial relationships are not captured for this synchronicity. To address the aforementioned perspectives, we propose the Spatio-Temporal Heterogeneous graph Attention Network (STHAN), where the key intuition is capturing the compound spatial relationships via meta-paths explicitly. We first construct a spatio-temporal heterogeneous graph including multiple spatial relationships and temporal relationships and use meta-paths to depict compound spatial relationships. To capture the heterogeneity, we use hierarchical attention, which contains node level attention and meta-path level attention. The synchronicity between temporal relationships and spatial relationships, including compound ones, is modeled in meta-path-level attention. Our framework outperforms state-of-the-art models by reducing 6.58%, 4.57%, and 4.20% of WMAPE in experiments on three real-world datasets, respectively.
关键词	Transportation demand prediction heterogeneous graph convolution spatio-temporal prediction
URL	查看原文
收录类别	SCI ; EI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering
WOS记录号	WOS:000968145900009
出版者	ASSOC COMPUTING MACHINERY
EI入藏号	20231814034298
EI主题词	Forecasting
EI分类号	716.1 Information Theory and Signal Processing ; 723.2 Data Processing and Image Processing ; 921.4 Combinatorial Mathematics, Includes Graph Theory, Set Theory
原始文献类型	Journal article (JA)
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/286565
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_张海鹏组
通讯作者	Yu, Zhe; Cao, Shaosheng; Zhang, Haipeng
作者单位	1.ShanghaiTech Univ, Sch Informat Sci & Technol, Middle Huaxia Rd, Shanghai 201210, Peoples R China 2.DiDi Chuxing, Hangzhou, Peoples R China 3.Zhejiang Univ, Zhejiang Univ Univ Illinois Urbana Champaign Inst, Zhijiang Rd, Haining 314400, Peoples R China
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Ling, Shuai,Yu, Zhe,Cao, Shaosheng,et al. STHAN: Transportation Demand Forecasting with Compound Spatio-Temporal Relationships[J]. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA,2023,17(4).
APA	Ling, Shuai,Yu, Zhe,Cao, Shaosheng,Zhang, Haipeng,&Hu, Simon.(2023).STHAN: Transportation Demand Forecasting with Compound Spatio-Temporal Relationships.ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA,17(4).
MLA	Ling, Shuai,et al."STHAN: Transportation Demand Forecasting with Compound Spatio-Temporal Relationships".ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 17.4(2023).