Research map / Time series / Long-term forecasting
Spatio-Temporal Meta-Graph Learning for Traffic Forecasting
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 |
|---|---|---|---|
| Add the Meta-Graph Learner to the adaptive-graph GCRN baseline (ablation) | MegaCRN · METR-LA, all horizons | MAE: 3.01 -> 2.89 | Helped |
| Add the Meta-Graph Learner to the adaptive-graph GCRN baseline (ablation) | MegaCRN · PEMS-BAY, all horizons | MAE: 1.61 -> 1.54 | Helped |
| Add the Meta-Graph Learner to the adaptive-graph GCRN baseline (ablation) | MegaCRN · EXPY-TKY, all horizons | MAE: 6.79 -> 6.44 | Helped |
| Add the Meta-Node Bank to momentary-graph GCRN (ablation) | MegaCRN · METR-LA, all horizons | MAE: 2.96 -> 2.89 | Helped |
| Add the Meta-Node Bank to momentary-graph GCRN (ablation) | MegaCRN · PEMS-BAY, all horizons | MAE: 1.62 -> 1.54 | Helped |
| Add the Meta-Node Bank to momentary-graph GCRN (ablation) | MegaCRN · EXPY-TKY, all horizons | MAE: 6.68 -> 6.44 | Helped |
| Add the Hyper-Network and meta-graph generation to Memory GCRN (ablation) | MegaCRN · METR-LA, all horizons | MAE: 2.97 -> 2.89 | Helped |
| Add the Hyper-Network and meta-graph generation to Memory GCRN (ablation) | MegaCRN · PEMS-BAY, all horizons | MAE: 1.60 -> 1.54 | Helped |
| Add the Hyper-Network and meta-graph generation to Memory GCRN (ablation) | MegaCRN · EXPY-TKY, all horizons | MAE: 6.55 -> 6.44 | Helped |
| Use MegaCRN instead of the strongest listed MAE baseline at each horizon | MegaCRN · METR-LA, horizons 3, 6, and 12 | MAE: 2.56 -> 2.52; 3.01 -> 2.93; 3.43 -> 3.38 | Helped |
| Use MegaCRN instead of the strongest listed MAE baseline at each horizon | MegaCRN · PEMS-BAY, horizons 3, 6, and 12 | MAE: 1.23 -> 1.28; 1.63 -> 1.60; 1.92 -> 1.88 | Mixed |
| Use MegaCRN instead of the strongest listed MAE baseline at each horizon | MegaCRN · EXPY-TKY, horizons 1, 3, and 6 | MAE: 5.86 -> 5.81; 6.49 -> 6.44; 6.81 -> 6.83 | Mixed |
Closest papers by meaning
- Spatio-Temporal Graph Structure Learning for Traffic Forecasting (AAAI 2020 · similarity 0.93)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (AAAI 2025 · similarity 0.90)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.90)
- Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting (AAAI 2024 · similarity 0.90)
- TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts (ICLR 2024 · similarity 0.89)
- Spatiotemporal-aware Trend-Seasonality Decomposition Network for Traffic Flow Forecasting (AAAI 2025 · similarity 0.89)
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.