Research map / Graph learning / Knowledge and temporal graphs
Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction
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 STGNPP rather than FNN-TPP | Traffic congestion event prediction · Beijing | NLL: 5.46* $\pm$ 0.05 -> 4.87 $\pm$ 0.03 | Helped |
| Use STGNPP rather than FNN-TPP | Traffic congestion event prediction · Chengdu | MAE-t (min): 27.13* $\pm$ 0.14 -> 24.52 $\pm$ 0.10 | Helped |
| Replace the spatio-temporal graph learning module with Graph WaveNet (ablation) | STGNPP · Beijing and Chengdu | MAE-t: 16.95 -> 17.12; 24.52 -> 24.91 | Hurt |
| Remove all GCN layers (ablation) | STGNPP · Beijing and Chengdu | MAE-t: 16.95 -> 18.17; 24.52 -> 26.34 | Hurt |
| Remove Transformer layers (ablation) | STGNPP · Beijing and Chengdu | MAE-t: 16.95 -> 18.45; 24.52 -> 27.10 | Hurt |
| Replace continuous GRU with fully connected networks (ablation) | STGNPP · Beijing and Chengdu | MAE-t: 16.95 -> 18.68; 24.52 -> 27.89 | Hurt |
| Replace continuous GRU with discrete GRU (ablation) | STGNPP · Beijing and Chengdu | MAE-t: 16.95 -> 18.38; 24.52 -> 27.65 | Hurt |
| Remove periodic gated unit from intensity function (ablation) | STGNPP · Beijing and Chengdu | MAE-t: 16.95 -> 18.29; 24.52 -> 26.11 | Hurt |
Closest papers by meaning
- Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting (AAAI 2024 · similarity 0.91)
- Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting (AAAI 2021 · similarity 0.91)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (AAAI 2025 · similarity 0.90)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.89)
- Spatiotemporal-aware Trend-Seasonality Decomposition Network for Traffic Flow Forecasting (AAAI 2025 · similarity 0.88)
- TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts (ICLR 2024 · 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.