Research map / Graph learning / Graph algorithms and clustering
GMDNet: A Graph-Based Mixture Density Network for Estimating Packages’ Multimodal Travel Time Distribution
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 GMDNet instead of KDE | Package travel-time distribution estimation · D1 | logL: -2.02 -> -0.73 ± 0.02 | Helped |
| Use GMDNet instead of KDE | Package travel-time distribution estimation · D2 | CRPS: 1.35 -> 1.21 ± 0.01 | Helped |
| Train with EM rather than gradient descent | GMDNet · D1 | MAE (h): 1.92 ± 0.08 -> 1.89 ± 0.03 | Helped |
| Train with EM rather than gradient descent | GMDNet · D2 | CRPS: 1.23 ± 0.03 -> 1.21 ± 0.01 | Helped |
| Replace graph-cooperated route encoding with an MLP (ablation) | GMDNet · D1 | MAE, MAPE, logL, and CRPS | Hurt |
| Remove mutual-correlation modeling among route edges (ablation) | GMDNet · D1 | MAE, MAPE, logL, and CRPS | Hurt |
| Use one mixture component instead of multiple components (ablation) | GMDNet · D1 | logL and CRPS | Hurt |
Closest papers by meaning
- When, Where, What: Structural Guarantees for Travel Time Prediction on Temporal Graphs (NeurIPS 2026 · similarity 0.81)
- Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction (CVPR 2019 · similarity 0.79)
- TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling (AAAI 2024 · similarity 0.79)
- SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark (NeurIPS 2026 · similarity 0.77)
- TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts (ICLR 2024 · similarity 0.77)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.76)
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.