BiST: A Lightweight and Efficient Bi-directional Model for Spatiotemporal Prediction
Summary: Introduces BiST, a bi-directional spatiotemporal predictor that injects label information via a spatiotemporal dynamic theory: MLP-only forward path plus a decoupled residual backward correction smoothed by diffusion. Matches SOTA (+8.13%) with far lower compute/memory. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Jiaming Ma (University of Science and Technology Beijing)
- 2. Binwu Wang (University of Science and Technology Beijing)
- 3. Pengkun Wang (University of Science and Technology Beijing)
- 4. Zhengyang Zhou (University of Science and Technology Beijing)
- 5. Xu Wang (University of Science and Technology Beijing)
- 6. Yang Wang (University of Science and Technology Beijing)
BibTeX Citation
@article{ma_vldb25,
title = {{BiST: A Lightweight and Efficient Bi-directional Model for Spatiotemporal Prediction}},
author = {Ma, Jiaming and Wang, Binwu and Wang, Pengkun and Zhou, Zhengyang and Wang, Xu and Wang, Yang},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {6},
pages = {1663--1676},
doi = {10.14778/3725688.3725697},
url = {https://doi.org/10.14778/3725688.3725697},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
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 |
|---|---|---|---|---|
| 4,589 | Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting | 2022 | VLDB | 6.6162897e-05 |
| 6,078 | Multiple Time Series Forecasting with Dynamic Graph Modeling | 2024 | VLDB | 5.9850223e-05 |
Previous
Page 1 / 1
Next