Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting
Summary: Decouples diffusion and inherent time signals in traffic data via a data-driven DSTF with an estimation gate and residual decomposition. D2STGNN adds dynamic graph learning to model evolving spatial-temporal relations, delivering state-of-the-art results on four real-world datasets. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zezhi Shao (Chinese Academy of Sciences; University of Chinese Academy of Sciences)
- 2. Zhao Zhang (Chinese Academy of Sciences)
- 3. Wei Wei (Huazhong University of Science and Technology)
- 4. Fei Wang (Chinese Academy of Sciences)
- 5. Yongjun Xu (Chinese Academy of Sciences)
- 6. Xin Cao (University of New South Wales)
- 7. Christian S. Jensen (Aalborg University)
BibTeX Citation
@article{shao_vldb22,
title = {{Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting}},
author = {Shao, Zezhi and Zhang, Zhao and Wei, Wei and Wang, Fei and Xu, Yongjun and Cao, Xin and Jensen, Christian S.},
journal = {PVLDB},
series = {{VLDB} '22},
volume = {15},
number = {11},
pages = {2733--2746},
doi = {10.14778/3551793.3551827},
url = {https://doi.org/10.14778/3551793.3551827},
year = {2022}
}
Incoming Citations (Sorted by Pagerank)
Showing 5 of 5 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 4,038 | BigST: Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks | 2024 | VLDB | 6.9431109e-05 |
| 8,503 | Fight Fire with Fire: Towards Robust Graph Neural Networks on Dynamic Graphs via Actively Defense | 2024 | VLDB | 5.4132367e-05 |
| 10,833 | BiST: A Lightweight and Efficient Bi-directional Model for Spatiotemporal Prediction | 2025 | VLDB | 5.093636e-05 |
| 10,854 | Scalable Pre-Training of Compact Urban Spatio-Temporal Predictive Models on Large-Scale Multi-Domain Data | 2025 | VLDB | 5.093636e-05 |
| 10,883 | TEAM: Topological Evolution-aware Framework for Traffic Forecasting | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,768 | DeepTRANS: A Deep Learning System for Public Bus Travel Time Estimation using Traffic Forecasting | 2020 | VLDB | 7.1406582e-05 |
| 3,899 | MDTP: A Multi-source Deep Traffic Prediction Framework over Spatio-Temporal Trajectory Data | 2021 | VLDB | 7.0361711e-05 |
Previous
Page 1 / 1
Next