Research map / Video / Video segmentation and tracking
Incomplete Label Multi-Task Ordinal Regression for Spatial Event Scale Forecasting
Yuyang Gao, Liang Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 adjacent-location threshold regularization (MITOR-I -> MITOR-II) (ablation) | MITOR-I · Civil unrest Mexico | MZE: 0.0967 -> 0.0875 | Improved |
| add threshold regularization (MITOR-I -> MITOR-II) (ablation) | MITOR-I · Civil unrest Argentina | MZE: 0.0161 -> 0.0158 | No clear effect |
| add threshold regularization (MITOR-I -> MITOR-II) (ablation) | MITOR-I · 2011-2012 US flu | MZE: 0.1148 -> 0.1145 | No clear effect |
| add threshold regularization (MITOR-I -> MITOR-II) (ablation) | MITOR-I · 2013-2014 US flu | MAE: 0.3473 -> 0.3466 | No clear effect |
| multi-task ordinal regression with l2,1 sparsity and per-location thresholds vs single POM | POM · 2011-2012 US flu | MZE: 0.2250 -> 0.1145 | Improved |
| multi-task ordinal regression vs single POM | POM · 2013-2014 US flu | MZE: 0.3036 -> 0.1794 | Improved |
| multi-task ordinal regression vs POM | POM · Civil unrest Brazil | MZE: 0.0626 -> 0.0339 | Improved |
| large beta (threshold regularization weight) (ablation) | MITOR-II · Mexico and 2011-12 flu | MZE/MAE | Hurt |
| alpha (l2,1 weight) too small or too large (ablation) | MITOR-II · Mexico and 2011-12 flu | MZE/MAE | Hurt |
Closest papers by meaning
- SPATIALEPIBENCH: Benchmarking Spatial Information and Epidemic Priors in Forecasting (NeurIPS 2026 · similarity 0.86)
- Aligning Time-series by Local Trends: Applications in Public Health (AAAI 2025 · similarity 0.83)
- Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach (NeurIPS 2025 · similarity 0.83)
- ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data (AAAI 2025 · similarity 0.83)
- Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment (NeurIPS 2024 · similarity 0.82)
- GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models Through Statistically-Guided Geo-Prototyping (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.
