Time-Evolving Graph Convolutional Recurrent Network for Traffic Prediction
Accurate traffic prediction is crucial to the construction of intelligent transportation systems. This task remains challenging because of the complicated and dynamic spatiotemporal dependency in traffic networks. While various graph-based spatiotemporal networks have been proposed for traffic predi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/6/2842 |
| _version_ | 1827650127862431744 |
|---|---|
| author | Weimin Mai Junxin Chen Xiang Chen |
| author_facet | Weimin Mai Junxin Chen Xiang Chen |
| author_sort | Weimin Mai |
| collection | DOAJ |
| description | Accurate traffic prediction is crucial to the construction of intelligent transportation systems. This task remains challenging because of the complicated and dynamic spatiotemporal dependency in traffic networks. While various graph-based spatiotemporal networks have been proposed for traffic prediction, most of them rely on predefined graphs from different views or static adaptive matrices. Some implicit dynamics of inter-node dependency may be neglected, which limits the performance of prediction. To address this problem and make more accurate predictions, we propose a traffic prediction model named Time-Evolving Graph Convolution Recurrent Network (TEGCRN), which takes advantage of time-evolving graph convolution to capture the dynamic inter-node dependency adaptively at different time slots. Specifically, we first propose a tensor-composing method to generate adaptive time-evolving adjacency graphs. Based on these time-evolving graphs and a predefined distance-based graph, a graph convolution module with mix-hop operation is applied to extract comprehensive inter-node information. Then the resulting graph convolution module is integrated into the Recurrent Neural Network structure to form an general predicting model. Experiments on two real-world traffic datasets demonstrate the superiority of TEGCRN over multiple competitive baseline models, especially in short-term prediction, which also verifies the effectiveness of time-evolving graph convolution in capturing more comprehensive inter-node dependency. |
| first_indexed | 2024-03-09T20:10:06Z |
| format | Article |
| id | doaj.art-ce5984c40dc24864a9054a4c19ad76da |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T20:10:06Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ce5984c40dc24864a9054a4c19ad76da2023-11-24T00:20:08ZengMDPI AGApplied Sciences2076-34172022-03-01126284210.3390/app12062842Time-Evolving Graph Convolutional Recurrent Network for Traffic PredictionWeimin Mai0Junxin Chen1Xiang Chen2School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou 510006, ChinaSchool of Electronics and Information Technology, Sun Yat-sen University, Guangzhou 510006, ChinaSchool of Electronics and Information Technology, Sun Yat-sen University, Guangzhou 510006, ChinaAccurate traffic prediction is crucial to the construction of intelligent transportation systems. This task remains challenging because of the complicated and dynamic spatiotemporal dependency in traffic networks. While various graph-based spatiotemporal networks have been proposed for traffic prediction, most of them rely on predefined graphs from different views or static adaptive matrices. Some implicit dynamics of inter-node dependency may be neglected, which limits the performance of prediction. To address this problem and make more accurate predictions, we propose a traffic prediction model named Time-Evolving Graph Convolution Recurrent Network (TEGCRN), which takes advantage of time-evolving graph convolution to capture the dynamic inter-node dependency adaptively at different time slots. Specifically, we first propose a tensor-composing method to generate adaptive time-evolving adjacency graphs. Based on these time-evolving graphs and a predefined distance-based graph, a graph convolution module with mix-hop operation is applied to extract comprehensive inter-node information. Then the resulting graph convolution module is integrated into the Recurrent Neural Network structure to form an general predicting model. Experiments on two real-world traffic datasets demonstrate the superiority of TEGCRN over multiple competitive baseline models, especially in short-term prediction, which also verifies the effectiveness of time-evolving graph convolution in capturing more comprehensive inter-node dependency.https://www.mdpi.com/2076-3417/12/6/2842traffic predictionspatiotemporal networkgraph convolutional networktime-evolving graphsgraph generation |
| spellingShingle | Weimin Mai Junxin Chen Xiang Chen Time-Evolving Graph Convolutional Recurrent Network for Traffic Prediction Applied Sciences traffic prediction spatiotemporal network graph convolutional network time-evolving graphs graph generation |
| title | Time-Evolving Graph Convolutional Recurrent Network for Traffic Prediction |
| title_full | Time-Evolving Graph Convolutional Recurrent Network for Traffic Prediction |
| title_fullStr | Time-Evolving Graph Convolutional Recurrent Network for Traffic Prediction |
| title_full_unstemmed | Time-Evolving Graph Convolutional Recurrent Network for Traffic Prediction |
| title_short | Time-Evolving Graph Convolutional Recurrent Network for Traffic Prediction |
| title_sort | time evolving graph convolutional recurrent network for traffic prediction |
| topic | traffic prediction spatiotemporal network graph convolutional network time-evolving graphs graph generation |
| url | https://www.mdpi.com/2076-3417/12/6/2842 |
| work_keys_str_mv | AT weiminmai timeevolvinggraphconvolutionalrecurrentnetworkfortrafficprediction AT junxinchen timeevolvinggraphconvolutionalrecurrentnetworkfortrafficprediction AT xiangchen timeevolvinggraphconvolutionalrecurrentnetworkfortrafficprediction |