Research map / Label-efficient and robust learning / Recognition and long-tail
Community-Aware Multi-Task Transportation Demand 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 Ada-MSTNet instead of the strongest baseline | Community-aware transportation demand prediction · BEIJING, τ=1 | RMSE: 13.51 -> 11.67 | Helped |
| Use Ada-MSTNet instead of the strongest baseline | Community-aware transportation demand prediction · BEIJING, τ=2 | RMSE: 14.48 -> 12.36 | Helped |
| Use Ada-MSTNet instead of the strongest baseline | Community-aware transportation demand prediction · BEIJING, τ=3 | MAE: 8.31 -> 7.40 | Helped |
| Use Ada-MSTNet instead of the strongest baseline | Community-aware transportation demand prediction · SHANGHAI, τ=3 | RMSE: 18.57 -> 15.27 | Helped |
| Combine region-view and community-view graphs rather than using either view alone (ablation) | Ada-MSTNet · BEIJING | RMSE | Helped |
| Use region-view graphs rather than community-view graphs alone (ablation) | Ada-MSTNet · BEIJING | RMSE | Helped |
| Combine GNN and GRU rather than using either component alone (ablation) | Ada-MSTNet · BEIJING | RMSE | Helped |
| Use GAT alone rather than GRU alone (ablation) | Ada-MSTNet · BEIJING | RMSE | Helped |
| Adaptively group tasks instead of using no grouping or precomputed grouping (ablation) | Ada-MSTNet · BEIJING | RMSE | Helped |
| Use an input length of 15 (ablation) | Ada-MSTNet · BEIJING | RMSE | Helped |
| Increase task groups to K ≥ 4 (ablation) | Ada-MSTNet · BEIJING | RMSE | Helped |
| Increase hidden dimension from 64 to 512 (ablation) | Ada-MSTNet · BEIJING | RMSE | Helped |
Closest papers by meaning
- Coupled Layer-wise Graph Convolution for Transportation Demand Prediction (AAAI 2021 · similarity 0.88)
- Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction (AAAI 2019 · similarity 0.88)
- Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting (AAAI 2019 · similarity 0.87)
- Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework (NeurIPS 2024 · similarity 0.84)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.84)
- Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach (NeurIPS 2025 · similarity 0.84)
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.