Research map / Time series / Long-term forecasting
Nested Spatio-Temporal Time Series Forecasting
YingHao Ai, Yukai Zhou, Ruoxi Jiang, Junyi An, Chao Qu, Zhijian Zhou, Shiyu Wang, Fenglei Cao, Zenglin Xu, Furao Shen, Yuan Qi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add cross-attention between regional and nodal representations (ablation) | NeST · GBA | MAE: 19.76 -> 18.73 | Improved |
| add cross-attention between regional and nodal representations (ablation) | NeST · GLA | MAE: 19.00 -> 17.89 | Improved |
| use predicted future regional signals instead of past observations (ablation) | NeST · GBA | RMSE: 32.89 -> 31.85 | Improved |
| use predicted future regional signals instead of past observations (ablation) | NeST · GLA | MAE: 18.85 -> 17.89 | Improved |
| semantic partitioning instead of K-Means (ablation) | NeST · GBA | MAE: 18.93 -> 18.73 | Improved |
| semantic partitioning instead of distance-adjacency clustering (ablation) | NeST · GLA | MAE: 18.34 -> 17.89 | Improved |
| semantic partitioning instead of random partition (ablation) | NeST · GBA | MAPE (%): 14.27 -> 12.89 | Improved |
| semantic partitioning instead of random-node representatives (ablation) | NeST · GBA | MAE: 19.44 -> 18.73 | Improved |
| number of regions M=0.2N instead of 0.1N or 0.3N (ablation) | NeST · GBA | MAE: 19.06 -> 18.73 (0.1N), 19.29 (0.3N) | Improved |
| NeST instead of PatchSTG at 48-step rollout | NeST · GLA (48-step auto-regressive) | MAE: 32.43 -> 30.03 | Improved |
| NeST instead of PatchSTG training | NeST · GBA runtime | training time (s/epoch): 185 -> 75 | Improved |
| NeST instead of PatchSTG inference | NeST · GBA runtime | inference time (s): 32 -> 20 | Improved |
Closest papers by meaning
- How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning (NeurIPS 2025 · similarity 0.88)
- Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling (ICML 2024 · similarity 0.88)
- Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting (ICLR 2025 · similarity 0.87)
- Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach (NeurIPS 2025 · similarity 0.87)
- Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting (NeurIPS 2025 · similarity 0.87)
- ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
