Research map / Time series / Causal and generative time series
Interpretable Sequence Learning for Covid-19 Forecasting
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 covariate encoders rather than fixed transition rates (ablation) | Interpretable Sequence Learning · US states, 14-day deaths | MAE: 87.3 -> 50.0; 76.1 -> 37.5; 71.0 -> 39.3 | Helped |
| Add the proposed extra compartments and their supervision (ablation) | Interpretable Sequence Learning · US states, 14-day deaths | MAE: 50.0 -> 32.9; 37.5 -> 23.8; 39.3 -> 26.5 | Helped |
| Add covariate encoders to the full compartment model (ablation) | Interpretable Sequence Learning · US states, 14-day deaths | MAE: 69.2 -> 32.9; 36.8 -> 23.8; 28.7 -> 26.5 | Helped |
| Add final fine-tuning on joint training and validation data (ablation) | Interpretable Sequence Learning · US states, 14-day deaths | MAE: 94.1 -> 32.9; 78.7 -> 23.8; 65.8 -> 26.5 | Helped |
| Add partial teacher forcing during training (ablation) | Interpretable Sequence Learning · US states, 14-day deaths | MAE: 792.6 -> 32.9; 1903.8 -> 23.8; 1289.7 -> 26.5 | Helped |
| Use the proposed model instead of YYG | US state-level forecasts · US states, 14-day deaths across prediction dates | MAE: 35.8 vs 46.5; 29.4 vs 37.7; 32.8 vs 26.5; 28.8 vs 22.3; 31.4 vs 32.1; 63.8 vs 64.2; 46.5 vs 35.1 | Mixed |
| Use the proposed model instead of Berkeley CLEP | County-level forecasts · US counties, 14-day deaths | MAE: 1.19 vs 1.91; 1.02 vs 1.79; 1.80 vs 3.24; 1.56 vs 3.10; 1.36 vs 3.20; 1.37 vs 3.32 | Helped |
| Train and evaluate with the more recent data version | Interpretable Sequence Learning · US states, 14-day deaths | MAE: 32.8 -> 29.6; 28.8 -> 23.2; 31.4 -> 20.9 | Helped |
Closest papers by meaning
- Transfer Graph Neural Networks for Pandemic Forecasting (AAAI 2021 · similarity 0.85)
- Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19 (AAAI 2021 · similarity 0.84)
- Cumulative Difference Learning VAE for Time-Series with Temporally Correlated Inflow-Outflow (AAAI 2024 · similarity 0.81)
- Reservoir Computing for Short High-Dimensional Time Series: an Application to SARS-CoV-2 Hospitalization Forecast (ICML 2024 · similarity 0.80)
- EARTH: Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph (ICML 2025 · similarity 0.80)
- 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.