Research map / Graph learning / Knowledge and temporal graphs
Hierarchical Graph Convolution Network for Traffic Forecasting
Kan Guo, Yongli Hu, Yanfeng Sun, Sean Qian, Junbin Gao, Baocai Yin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 hierarchical region-graph features and dynamic interaction with road-segment features | GWNET · JiNan | MAE: 3.16 -> 3.11 (1 hour); 3.52 -> 3.36 (2 hour) | Improved |
| add hierarchical region-graph features and dynamic interaction with road-segment features | GWNET · XiAn | MAE: 2.76 -> 2.75 (30 min); 3.03 -> 2.96 (1 hour); 3.44 -> 3.24 (2 hour) | Improved |
| add hierarchical region-graph features and dynamic interaction with road-segment features | GWNET · JiNan, 30 min | MAE: 2.89 -> 2.89 | No clear effect |
| add a region graph and region features (ablation) | HGCN · JiNan | MAE: 2.89 -> 2.89 (30 min); 3.15 -> 3.11 (1 hour); 3.43 -> 3.36 (2 hour) | Improved |
| add a region graph and region features (ablation) | HGCN · XiAn | MAE: 2.75 -> 2.75 (30 min); 3.00 -> 2.96 (1 hour); 3.34 -> 3.24 (2 hour) | Improved |
| use a dynamic transfer matrix instead of a fixed transfer matrix (ablation) | HGCN · JiNan | MAE: 2.91 -> 2.89 (30 min); 3.15 -> 3.11 (1 hour); 3.41 -> 3.36 (2 hour) | Improved |
| use a dynamic transfer matrix instead of a fixed transfer matrix (ablation) | HGCN · XiAn | MAE: 2.77 -> 2.75 (30 min); 3.02 -> 2.96 (1 hour); 3.30 -> 3.24 (2 hour) | Improved |
| increase the number of regions (ablation) | HGCN · JiNan and XiAn, 2 hour forecasting | MAE | Mixed |
Closest papers by meaning
- Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting (AAAI 2019 · similarity 0.92)
- Spatio-Temporal Graph Structure Learning for Traffic Forecasting (AAAI 2020 · similarity 0.91)
- Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting (NeurIPS 2020 · similarity 0.91)
- Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting (AAAI 2019 · similarity 0.91)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (AAAI 2025 · similarity 0.88)
- Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting (AAAI 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.
