期刊
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
卷 23, 期 5, 页码 3904-3924出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2020.3043250
关键词
Deep learning; Task analysis; Urban areas; Roads; Computer architecture; Accidents; Public transportation; Graph neural networks; GNNs; graph convolution network; GCN; graph; deep learning; traffic forecasting; traffic domain; ITS
资金
- National Key Research and Development Program of China [2019YFB2102100]
- National Natural Science Foundation of China [61802387]
- China's Post-Doctoral Science Fund [2019M663183]
- Shenzhen Basic Research Program [JCYJ20190812153212464, JCYJ20170818153016513]
- Shenzhen Engineering Research Center for Beidou Positioning Service Improvement Technology [XMHT20190101035]
- Science and Technology Development Fund of Macao S.A.R. (FDCT) [0015/2019/AKP]
- Shenzhen Discipline Construction Project for Urban Computing and Data Intelligence
- Youth Innovation Promotion Association of the Chinese Academy of Sciences (CAS) [2019349]
This article surveys graph-based deep learning architectures in the traffic domain, providing guidelines for problem formulation and graph construction, discussing shared deep learning techniques, and presenting graph neural network solutions for traffic challenges.
In recent years, various deep learning architectures have been proposed to solve complex challenges (e.g. spatial dependency, temporal dependency) in traffic domain, which have achieved satisfactory performance. These architectures are composed of multiple deep learning techniques in order to tackle various challenges in traffic tasks. Traditionally, convolution neural networks (CNNs) are utilized to model spatial dependency by decomposing the traffic network as grids. However, many traffic networks are graph-structured in nature. In order to utilize such spatial information fully, it's more appropriate to formulate traffic networks as graphs mathematically. Recently, various novel deep learning techniques have been developed to process graph data, called graph neural networks (GNNs). More and more works combine GNNs with other deep learning techniques to construct an architecture dealing with various challenges in a complex traffic task, where GNNs are responsible for extracting spatial correlations in traffic network. These graph-based architectures have achieved state-of-the-art performance. To provide a comprehensive and clear picture of such emerging trend, this survey carefully examines various graph-based deep learning architectures in many traffic applications. We first give guidelines to formulate a traffic problem based on graph and construct graphs from various kinds of traffic datasets. Then we decompose these graph-based architectures to discuss their shared deep learning techniques, clarifying the utilization of each technique in traffic tasks. What's more, we summarize some common traffic challenges and the corresponding graph-based deep learning solutions to each challenge. Finally, we provide benchmark datasets, open source codes and future research directions in this rapidly growing field.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据