Research map / Probabilistic and scientific modeling / Molecules and proteins
STELAR: Spatio-temporal Tensor Factorization with Latent Epidemiological Regularization
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 |
|---|---|---|---|
| Jointly fit nonnegative tensor factors with latent SIR regularization instead of using separate location-level forecasts | STELAR · County COVID-19 new infections, 10 days | RMSE: 18% lower RMSE | Helped |
| Jointly fit nonnegative tensor factors with latent SIR regularization instead of using separate location-level forecasts | STELAR · County COVID-19 new infections, 15 days | RMSE: 10% lower RMSE | Helped |
| Jointly fit nonnegative tensor factors with latent SIR regularization instead of using separate location-level forecasts | STELAR · County hospitalized patients, 10 days | RMSE: 21% lower RMSE | Helped |
| Jointly fit nonnegative tensor factors with latent SIR regularization instead of using separate location-level forecasts | STELAR · County hospitalized patients, 15 days | MAE: 25% lower MAE | Helped |
| Use STELAR rather than the strongest baseline | State-level COVID-19 new infections · State COVID-19 new infections | RMSE | Hurt |
| Remove latent SIR regularization (ν=0) (ablation) | STELAR · County COVID-19 new infections, 10 days | RMSE: 149.2 -> 127.5 | Hurt |
| Remove latent SIR regularization (ν=0) (ablation) | STELAR · County hospitalized patients, 15 days | RMSE: 46.8 -> 36.0 | Hurt |
| Remove latent SIR regularization (ν=0) (ablation) | STELAR · State COVID-19 new infections, 10 days | RMSE: 140.8 -> 117.8 | Hurt |
| Remove latent SIR regularization (ν=0) (ablation) | STELAR · State hospitalized patients, 15 days | MAE: 83.8 -> 75.2 | Helped |
| Replace joint optimization with the two-step unregularized procedure (ablation) | STELAR · County and state COVID-19 forecasts | RMSE | Mixed |
Closest papers by meaning
- Interpretable Sequence Learning for Covid-19 Forecasting (NeurIPS 2020 · similarity 0.83)
- Reservoir Computing for Short High-Dimensional Time Series: an Application to SARS-CoV-2 Hospitalization Forecast (ICML 2024 · similarity 0.81)
- SPATIALEPIBENCH: Benchmarking Spatial Information and Epidemic Priors in Forecasting (NeurIPS 2026 · similarity 0.80)
- EARTH: Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph (ICML 2025 · similarity 0.80)
- Aligning Time-series by Local Trends: Applications in Public Health (AAAI 2025 · similarity 0.79)
- Dynamics-Based Feature Augmentation of Graph Neural Networks for Variant Emergence Prediction (AAAI 2025 · similarity 0.79)
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.