Research map / Time series / Long-term forecasting
Inductive Graph Neural Networks for Spatiotemporal Kriging
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use IGNNK instead of GLTL | spatiotemporal kriging · METR-LA | RMSE: 9.668 -> 9.048 | Helped |
| Use IGNNK instead of OKriging | spatiotemporal kriging · NREL | RMSE: 3.470 -> 3.261 | Helped |
| Use IGNNK instead of OKriging | spatiotemporal kriging · USHCN | MAE: 1.999 -> 2.063 | Hurt |
| Use IGNNK instead of GLTL | spatiotemporal kriging · SeData | RMSE: 6.989 -> 6.863 | Helped |
| Use Gaussian distance adjacency rather than binary connectivity adjacency | IGNNK on PeMS-Bay · PeMS-Bay | RMSE: 9.245 -> 6.093 | Helped |
| Transfer the model trained on METR-LA to PeMS-Bay without retraining | IGNNK · PeMS-Bay (Gaussian adjacency) | R²: 0.525 | Helped |
| Transfer the model trained on SeData to PeMS-Bay without retraining | IGNNK · PeMS-Bay (binary adjacency) | R²: -0.388 | Hurt |
| Use binary adjacency instead of Gaussian distance adjacency | IGNNK on PeMS-Bay · PeMS-Bay | R²: 0.574 -> 0.161 | Hurt |
Closest papers by meaning
- KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategy (AAAI 2025 · similarity 0.92)
- Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling (ICML 2024 · similarity 0.90)
- Over-squashing in Spatiotemporal Graph Neural Networks (NeurIPS 2025 · similarity 0.88)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.88)
- Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data (AAAI 2024 · similarity 0.88)
- Designing Specialized Two-Dimensional Graph Spectral Filters for Spatial-Temporal Graph Modeling (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.