Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution

By Fuxian Li, Jie Feng, Huan Yan, Guangyin Jin, Depeng Jin, Yong Li. ACM Transactions on Knowledge Discovery from Data, 2021

668 citations recorded by the source corpus.

Traffic prediction is the cornerstone of intelligent transportation system. Accurate traffic forecasting is essential for the applications of smart cities, i.e., intelligent traffic management and urban planning. Although various methods are proposed for spatio-temporal modeling, they ignore the dynamic characteristics of correlations among locations on road network. Meanwhile, most Recurrent Neural Network based works are not efficient enough due to their recurrent operations. Additionally, there is a severe lack of fair comparison among different methods on the same datasets. To address the above challenges, in this article, we propose a novel traffic prediction framework, named Dynamic Graph Convolutional Recurrent Network (DGCRN). In DGCRN, hyper-networks are designed to leverage and extract dynamic characteristics from node attributes, while the parameters of dynamic filters are generated at each time step. We filter the node embeddings and then use them to generate dynamic graph, which is integrated with pre-defined static graph. As far as we know, we are first to employ a generation method to model fine topology of dynamic graph at each time step. Furthermore, to enhance efficiency and performance, we employ a training strategy for DGCRN by restricting the iteration number of decoder during forward and backward propagation. Finally, a reproducible standardized benchmark and a brand new representative traffic dataset are opened for fair comparison and further research. Extensive experiments on three datasets demonstrate that our model outperforms 15 baselines consistently. Source codes are available at https://github.com/tsinghua-fib-lab/Traffic-Benchmark.

Subfields: Building and Construction, Control and Systems Engineering, Transportation

View Paper: https://www.semanticscholar.org/paper/3d2c138a2c757b2483f927fea5395b41fc02c789

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

1. Junbo Zhang
2. Yu Zheng
3. Yuxuan Liang
4. Zezhi Shao
5. Fei Wang
6. Zhao Zhang
7. Yongjun Xu
8. Guangyin Jin

In Control and Systems Engineering

1. Zezhi Shao
2. Fei Wang
3. Zhao Zhang
4. Yu Zheng
5. Junbo Zhang
6. Yongjun Xu

In Transportation

1. Junbo Zhang
2. Yu Zheng
3. Yuxuan Liang
4. Zezhi Shao
5. Fei Wang
6. Zhao Zhang
7. Yongjun Xu
8. Xing Xie

Citations in the corpus

• Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey (2023, background): “Feature initialization-based adaptive graph learning methods perform adaptive graph structure learning based on the given inputs or the hidden states [82], [113], [121], [127], [174]–[177].”
• Spatio-Temporal Meta-Graph Learning for Traffic Forecasting (2022, neutral): “Due to the space limitation, we refer you to the recent surveys (Jiang et al. 2021; Jiang and Luo 2021; Li et al. 2021) on traffic forecasting with deep learning.”
• Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting (2022, background): “The feature H is dynamic for different training samples to reflect the dynamics of dependency graphs [19].”
• Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting (2022, neutral): “For METR-LA and PEMS-BAY, we use about 70% of data for training, 20% of data for testing, and the remaining 10% for validation [20, 21, 40, 41].”