BigST: Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks
Summary: BigST is a linear-complexity STGNN that encodes node-wise long-range sequences via a precomputable low-dimensional feature extractor and a linearized global spatial convolution to distill time-varying graph structure. Scales to ~100k-node road networks, delivering improved accuracy and runtime for long-horizon traffic forecasting versus quadratic-cost baselines. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jindong Han (Hong Kong University of Science and Technology)
- 2. Weijia Zhang (Hong Kong University of Science and Technology)
- 3. Hao Liu (Hong Kong University of Science and Technology)
- 4. Tao Tao (DiDi Chuxing Co., Ltd.)
- 5. Naiqiang Tan (DiDi Chuxing Co., Ltd.)
- 6. Hui Xiong (Hong Kong University of Science and Technology)
BibTeX Citation
@article{han_vldb24,
title = {{BigST: Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks}},
author = {Han, Jindong and Zhang, Weijia and Liu, Hao and Tao, Tao and Tan, Naiqiang and Xiong, Hui},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {5},
pages = {1081--1090},
doi = {10.14778/3641204.3641217},
url = {https://doi.org/10.14778/3641204.3641217},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,241 | FastGNAS: Accelerating and Scaling Graph Neural Architecture Search on Multi-GPUs via Ring-Based Model Migration | 2026 | SIGMOD | 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 |
| 10,862 | GraphSparseNet: a Novel Method for Large Scale Traffic Flow Prediction | 2025 | VLDB | 5.093636e-05 |
| 10,935 | Towards Pattern-aware Data Augmentation for Temporal Knowledge Graph Completion | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,793 | TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data | 2022 | VLDB | 9.7435472e-05 |
| 3,899 | MDTP: A Multi-source Deep Traffic Prediction Framework over Spatio-Temporal Trajectory Data | 2021 | VLDB | 7.0361711e-05 |
| 4,589 | Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting | 2022 | VLDB | 6.6162897e-05 |
| 5,129 | AutoCTS: Automated Correlated Time Series Forecasting | 2022 | VLDB | 6.3548172e-05 |
| 6,146 | METRO: A Generic Graph Neural Network Framework for Multivariate Time Series Forecasting | 2022 | VLDB | 5.9601852e-05 |
Previous
Page 1 / 1
Next