Research map / Probabilistic and scientific modeling / Dynamical systems
Learning from Imperfect Data: Robust Inference of Dynamic Systems Using Simulation-Based Generative Model
Hyunwoo Cho, Hyeontae Jo, Hyung Ju Hwang
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 |
|---|---|---|---|
| use SiGMoID (HyperPINN + W-GAN) instead of MAGI, FGPGM and AGM on noisy sparse data | SiGMoID · FitzHugh-Nagumo, NS data | trajectory RMSE (V): 0.103 -> 0.028 | Improved |
| use SiGMoID instead of MAGI on protein transduction NS data | SiGMoID · Protein transduction, NS data | trajectory RMSE x10^3 (S): 12.2 -> 0.3 | Improved |
| use SiGMoID instead of MAGI on Hes1 with missing component H | SiGMoID · Hes1, NSMC data | trajectory RMSE (H): 2.57 -> 1.96 | Improved |
| remove observations of component R (NS to NSMC) in FitzHugh-Nagumo (ablation) | SiGMoID · FitzHugh-Nagumo | trajectory RMSE (V): 0.028 -> 0.038 | Hurt |
| remove observations of all components except Rpp in protein transduction (ablation) | SiGMoID · Protein transduction | trajectory RMSE x10^3 (S): 0.3 -> 11.2 | Hurt |
| apply SiGMoID to Lorenz with Y and Z unobserved | SiGMoID · Lorenz system, NSMC data | trajectory accuracy | Improved |
Closest papers by meaning
- Structural Inference of Dynamical Systems with Conjoined State Space Models (NeurIPS 2024 · similarity 0.86)
- Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations (ICLR 2025 · similarity 0.85)
- Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs (ICLR 2024 · similarity 0.85)
- Semi-supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach (AAAI 2024 · similarity 0.85)
- Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data (ICLR 2025 · similarity 0.84)
- PGODE: Towards High-quality System Dynamics Modeling (ICML 2024 · similarity 0.84)
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.
