Research map / Graph learning / Knowledge and temporal graphs
Spatio-Temporal Graph Structure 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 learned graph structure (vs predefined graph) (ablation) | SLCNN without P3D · METR-LA (60 min) | MAE: 4.04 -> 3.42 | Helped |
| add P3D temporal convolution (ablation) | SLCNN · METR-LA (60 min) | MAE: 3.42 -> 3.30 | Helped |
| add P3D temporal convolution (ablation) | SLCNN · METR-LA | inference time: 2.54 -> 21.53 | Hurt |
| combine global and local SLC (vs only one) (ablation) | SLCNN · six traffic datasets | MAE | Helped |
| combine static and dynamic structure terms (vs only one) (ablation) | SLCNN · six traffic datasets | MAE | Helped |
| SLCNN vs GWN | traffic forecasting · PeMS-S / PeMS-BAY vs METR-LA, BJF, BRF, BRF-L | MAE | Mixed |
Closest papers by meaning
- Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting (AAAI 2019 · similarity 0.94)
- Spatio-Temporal Meta-Graph Learning for Traffic Forecasting (AAAI 2023 · similarity 0.93)
- Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting (NeurIPS 2020 · similarity 0.92)
- Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting (AAAI 2024 · similarity 0.90)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (AAAI 2025 · similarity 0.90)
- TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts (ICLR 2024 · 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.