Research map / Probabilistic and scientific modeling / Dynamical systems
Neural Collective Graphical Models for Estimating Spatio-Temporal Population Flow from Aggregated Data
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 |
|---|---|---|---|
| model transition probabilities with a neural network of time and location instead of VCGMM time clustering | collective graphical model · Tokyo | normalized absolute error: 0.167 -> 0.148 | Helped |
| model transition probabilities with a neural network of time and location instead of VCGMM time clustering | collective graphical model · Osaka | normalized absolute error: 0.250 -> 0.186 | Helped |
| model transition probabilities with a neural network of time and location instead of VCGMM time clustering | collective graphical model · Nagoya | normalized absolute error: 0.250 -> 0.227 | Helped |
| model transition probabilities with a neural network of time and location instead of VCGMM time clustering | collective graphical model · Beijing | normalized absolute error: 0.470 -> 0.408 | Helped |
| use time-varying neural transition model instead of time-invariant CGM | collective graphical model · Tokyo | normalized absolute error: 0.208 -> 0.148 | Helped |
| cluster time points (VCGMM) instead of per-time parameters (ICGM) | collective graphical model · Tokyo | normalized absolute error: 0.176 -> 0.167 | Helped |
Closest papers by meaning
- SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark (NeurIPS 2026 · similarity 0.84)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.83)
- Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach (ICML 2025 · similarity 0.82)
- Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling (ICML 2024 · similarity 0.82)
- ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data (AAAI 2025 · similarity 0.82)
- Generating Origin-Destination Matrices in Neural Spatial Interaction Models (NeurIPS 2024 · 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.