Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting

By Liangzhe Han, Bowen Du, Leilei Sun, Yanjie Fu, Yisheng Lv, Hui Xiong. Knowledge Discovery and Data Mining, 2021

339 citations recorded by the source corpus.

Dynamic Graph Neural Networks (DGNNs) have become one of the most promising methods for traffic speed forecasting. However, when adapting DGNNs for traffic speed forecasting, existing approaches are usually built on a static adjacency matrix (no matter predefined or self-learned) to learn spatial relationships among different road segments, even if the impact of two road segments can be changeable dynamically during a day. Moreover, the future traffic speed cannot only be related with the current traffic speed, but also be affected by other factors such as traffic volumes. To this end, in this paper, we aim to explore these dynamic and multi-faceted spatio-temporal characteristics inherent in traffic data for further unleashing the power of DGNNs for better traffic speed forecasting. Specifically, we design a dynamic graph construction method to learn the time-specific spatial dependencies of road segments. Then, a dynamic graph convolution module is proposed to aggregate hidden states of neighbor nodes to focal nodes by message passing on the dynamic adjacency matrices. Moreover, a multi-faceted fusion module is provided to incorporate the auxiliary hidden states learned from traffic volumes with the primary hidden states learned from traffic speeds. Finally, experimental results on real-world data demonstrate that our method can not only achieve the state-of-the-art prediction performances, but also obtain the explicit and interpretable dynamic spatial relationships of road segments.

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

View Paper: https://www.semanticscholar.org/paper/71ae7a93abd103a1f6820b446d24232a458ae75f

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. Wei Wei
6. Junbo Zhang
7. Yongjun Xu

In Transportation

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

Citations in the corpus

• Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey (2023, methodology): “net/ [18], [26], [118]–[122] NYC taxi https://www1.”
• Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting (2022, background): “Most of them explore the dynamic spatial dependency based on the feature of traffic conditions, ignoring either the constraints of the road network topology [13], or the time [50] or node [11] information.”
• PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction (2023, neutral): “…prediction (Li et al. 2018; Yu, Yin, and Zhu 2018; Wu et al. 2019; Ji et al. 2020; Chen et al. 2020; Ye et al. 2021; Wu et al. 2020; Zhang et al. 2021; Song et al. 2020; Li and Zhu 2021; Oreshkin et al. 2021; Han et al. 2021; Ji et al. 2022; Fang et al. 2021; Choi et al. 2022; Liu et al. 2022).”