Research map / Graph learning / Knowledge and temporal graphs
Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand 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 neighborhood graph (ablation) | ST-MGCN · Beijing | RMSE: 11.47 -> 10.78 | Helped |
| add functional similarity graph (ablation) | ST-MGCN · Beijing | RMSE: 11.42 -> 10.78 | Helped |
| add transportation connectivity graph (ablation) | ST-MGCN · Beijing | RMSE: 11.69 -> 10.78 | Helped |
| add multi-graph convolution | ST-GCN · Beijing | RMSE: 11.62 -> 11.20 | Helped |
| add multi-graph convolution | DCRNN · Beijing | RMSE: 12.02 -> 11.55 | Helped |
| contextual gated RNN instead of average pooling (ablation) | ST-MGCN · Beijing | RMSE: 12.74 -> 10.78 | Helped |
| add contextual gating to RNN (ablation) | ST-MGCN · Beijing | RMSE: 11.05 -> 10.78 | Helped |
| add RNN to contextual gating (ablation) | ST-MGCN · Beijing | RMSE: 11.82 -> 10.78 | Helped |
| add graph convolution in contextual gating (ablation) | ST-MGCN · Beijing | RMSE: 10.91 -> 10.78 | Helped |
| increase number of graph conv layers (ablation) | ST-MGCN · Beijing | RMSE | Mixed |
| increase polynomial order K (ablation) | ST-MGCN · Beijing | RMSE | Mixed |
Closest papers by meaning
- Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction (AAAI 2018 · similarity 0.90)
- Coupled Layer-wise Graph Convolution for Transportation Demand Prediction (AAAI 2021 · similarity 0.90)
- Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction (AAAI 2019 · similarity 0.88)
- Community-Aware Multi-Task Transportation Demand Prediction (AAAI 2021 · similarity 0.87)
- TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts (ICLR 2024 · similarity 0.83)
- Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting (ICLR 2025 · similarity 0.83)
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.