Research map / Probabilistic and scientific modeling / Dynamical systems
ODEBrain: Continuous-Time EEG Graph for Modeling Dynamic Brain Networks
Haohui Jia, Zheng Chen, Lingwei Zhu, Rikuto Kotoge, Jathurshan Pradeepkumar, Yasuko Matsubara, Jimeng Sun, Yasushi Sakurai, Takashi Matsubara
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 gate (adaptive vector field) (ablation) | ODEBRAIN · TUSZ 12s | AUROC: 0.867 -> 0.881 | Improved |
| add stochastic regularization (ablation) | ODEBRAIN · TUSZ 12s | F1: 0.462 -> 0.496 | Improved |
| use random gate coefficients instead of learned gate (ablation) | ODEBRAIN · TUSZ 12s | AUROC: 0.881 -> 0.860 | Hurt |
| use temporal-spatial initial state instead of spatial-only (ablation) | ODEBRAIN · TUSZ | AUROC: 0.862 -> 0.877 | Improved |
| use temporal-spatial initial state instead of mixed (ablation) | ODEBRAIN · TUSZ | AUROC: 0.851 -> 0.877 | Improved |
| use structural forecasting loss instead of reconstruction-only or raw-signal forecasting (ablation) | ODEBRAIN · TUSZ | AUROC | Improved |
| add graph embedding target to the objective (ablation) | ODEBRAIN · graph similarity (GJI) | similarity: 0.53 -> 0.63 | Improved |
| lengthen forecast horizon (ablation) | ODEBRAIN · TUSZ | AUROC: 1s -> 3s -> 11s | Hurt |
| use graphical lasso instead of norm graph regularizer (ablation) | ODEBRAIN · TUSZ | AUROC: 0.881 -> 0.872 | Hurt |
| use graphical lasso regularizer instead of norm (ablation) | ODEBRAIN · TUSZ | Recall: 0.605 -> 0.613 | Improved |
| lengthen input from 12s to 60s | ODEBRAIN · TUSZ | AUROC: 0.881 -> 0.828 | Hurt |
| use ODEBRAIN instead of latent-ODE | ODEBRAIN · TUSZ 12s | AUROC: 0.849 -> 0.881 | Improved |
Closest papers by meaning
- Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics (NeurIPS 2024 · similarity 0.86)
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · similarity 0.86)
- EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks (NeurIPS 2025 · similarity 0.86)
- Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics (AAAI 2024 · similarity 0.85)
- Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems (NeurIPS 2024 · similarity 0.85)
- THD-BAR: Topology Hierarchical Derived Brain Autoregressive Modeling for EEG Generic Representations (NeurIPS 2025 · similarity 0.85)
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.
