Research map / Graph learning / Knowledge and temporal graphs
Dynamic Spatial-Temporal Graph Convolutional Neural Networks 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 |
|---|---|---|---|
| dynamic Laplacian estimator (DGCNN) vs fixed-Laplacian STGCN | graph conv traffic forecaster · NYC 45 min | MAE: 3.44 -> 3.29 | Helped |
| DGCNN vs graph-CNN baselines under corrupted sensor inputs | traffic forecasting · PeMS-50/142/228 with faults | MAE: 10% - 25% | Helped |
| increase number of expansion terms I in Laplacian estimator (ablation) | DGCNN · PeMS-50 | MAE | Helped |
| randomly permute spatial order of input (ablation) | DGCNN · NYC / PeMS | accuracy | No clear effect |
Closest papers by meaning
- Spatio-Temporal Graph Structure Learning for Traffic Forecasting (AAAI 2020 · similarity 0.94)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (AAAI 2025 · similarity 0.91)
- Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting (AAAI 2024 · similarity 0.91)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.90)
- TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts (ICLR 2024 · similarity 0.90)
- Designing Specialized Two-Dimensional Graph Spectral Filters for Spatial-Temporal Graph Modeling (AAAI 2025 · similarity 0.88)
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.