Research map / Graph learning / Knowledge and temporal graphs
Adaptive Frequency Pathways for Spatiotemporal Forecasting
Yanjun Qin, Yuchen Fang, Xinke Jiang, Hao Miao, Xiaoming Tao
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 frequency decomposition (ablation) | AdaFre · PeMSD3 | MAPE (%): 16.24% -> 15.04% | Improved |
| add frequency decomposition (ablation) | AdaFre · PeMSD4 | MAE: 18.35 -> 17.89 | Improved |
| add frequency decomposition (ablation) | AdaFre · PeMSD7 | MAPE (%): 8.42% -> 7.85% | Improved |
| use frequency-aligned spectral embeddings instead of one shared embedding (ablation) | AdaFre · PeMSD3 | MAE: 14.44 -> 14.27 | Improved |
| use frequency-aligned spectral embeddings instead of one shared embedding (ablation) | AdaFre · PeMSD7 | MAE: 18.78 -> 18.58 | Improved |
| add adaptive path selection and importance weighting (ablation) | AdaFre · PeMSD4 | MAPE (%): 12.79% -> 11.97% | Improved |
| add adaptive path selection and importance weighting (ablation) | AdaFre · PeMSD8 | MAE: 13.41 -> 12.99 | Improved |
| use input length 288 rather than shorter or longer (ablation) | AdaFre · PeMSD4, PeMSD8 | forecast error | Improved |
| use P=4 frequency bands rather than 2, 3 or 5 (ablation) | AdaFre · PeMSD4, PeMSD8 | forecast error | Improved |
| wrap STID backbone with adaptive frequency pathways | AdaFre · PeMSD3 | MAE: 15.33 -> 14.27 | Improved |
| sparse top-K frequency routing versus heavy baselines | AdaFre · PeMSD4 | time per epoch: 189s (HimNet) -> 23s | Improved |
| AdaFre vs STID cost | AdaFre · PeMSD4 | time per epoch: 15s -> 23s | Hurt |
Closest papers by meaning
- Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach (NeurIPS 2025 · similarity 0.88)
- Wavelet-Driven Spatiotemporal Predictive Learning: Bridging Frequency and Time Variations (AAAI 2024 · similarity 0.87)
- Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting (NeurIPS 2025 · similarity 0.87)
- Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model (NeurIPS 2024 · similarity 0.86)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.86)
- How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning (NeurIPS 2025 · similarity 0.85)
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.
