Research map / Graph learning / Knowledge and temporal graphs
DeepSTN+: Context-Aware Spatial-Temporal Neural Network for Crowd Flow Prediction in Metropolis
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 |
|---|---|---|---|
| DeepSTN+ vs ST-ResNet | crowd flow prediction · MobileBJ | RMSE: 42.19 -> 36.29 | Helped |
| DeepSTN+ vs ST-ResNet | crowd flow prediction · BikeNYC | RMSE: 6.475 -> 5.955 | Helped |
| add ResPlus units (ablation) | DeepSTN · MobileBJ | RMSE: 39.85 -> 37.69 | Helped |
| add ResPlus units (ablation) | DeepSTN · BikeNYC | RMSE: 6.213 -> 6.128 | Helped |
| add PoI with time information (ablation) | DeepSTN · MobileBJ | RMSE: 39.85 -> 37.62 | Helped |
| add time information to PoI (ablation) | DeepSTN+PoI · MobileBJ | RMSE: 39.12 -> 37.62 | Helped |
| add multi-scale fusion (+con) (ablation) | DeepSTN+plus+PoI*time · MobileBJ | RMSE: 36.29 -> 36.89 | Hurt |
| add multi-scale fusion (+con) (ablation) | DeepSTN+plus+PoI*time · BikeNYC | RMSE: 5.984 -> 5.955 | Helped |
| early fusion single-branch (DeepSTN) instead of ST-ResNet (ablation) | crowd flow prediction · MobileBJ | RMSE: 42.19 -> 39.85 | Helped |
| increase ConvPlus separated channels beyond 8 (ablation) | DeepSTN+ · MobileBJ/BikeNYC | RMSE | Hurt |
Closest papers by meaning
- Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction (AAAI 2017 · similarity 0.91)
- Generic and Dynamic Graph Representation Learning for Crowd Flow Modeling (AAAI 2023 · similarity 0.85)
- Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder (AAAI 2024 · similarity 0.84)
- FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction (ICML 2024 · similarity 0.83)
- Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation (ICLR 2024 · similarity 0.83)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (AAAI 2025 · similarity 0.82)
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.