ShanghaiTech University Knowledge Management System
STHAN: Transportation Demand Forecasting with Compound Spatio-Temporal Relationships | |
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). |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
修改评论
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。