Research map / Graph learning / Knowledge and temporal graphs
Newton–Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems
Lingbing Guo, Weiqing Wang, Zhuo Chen, Ningyu Zhang, Zequn Sun, Yixuan Lai, Qiang Zhang, Huajun Chen
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 |
|---|---|---|---|
| Wrap EGNN with NC+ (k=2) | EGNN · N-body 500 train, 5,3,3 | prediction error (x10^-2): 4.59 -> 3.96 | Improved |
| Wrap GMN with NC (k=2) | GMN · N-body 500 train, 5,3,3 | prediction error (x10^-2): 4.08 -> 2.99 | Improved |
| Wrap RF with NC+ (k=2) | RF · N-body 500 train, 5,3,3 | prediction error (x10^-2): 7.73 -> 7.06 | Improved |
| Wrap EGNN with NC | EGNN · MD17 Aspirin | prediction error (x10^-2): 14.41 -> 9.63 | Improved |
| Wrap RF with NC | RF · MD17 Benzene | prediction error (x10^-2): 103.72 -> 63.22 | Improved |
| Wrap GMN with NC | GMN · MD17 Ethanol | prediction error (x10^-2): 4.83 -> 4.83 | No clear effect |
| Wrap GMN with NC | GMN · Motion capture | prediction error (x10^-2): 43.9 -> 30.0 | Improved |
| Add intermediate velocity supervision (NC+ vs NC) | GMN · N-body 500 train, 1,2,0 | prediction error (x10^-2): 1.55 -> 1.57 | No clear effect |
| Add intermediate velocity supervision (NC+ vs NC) | GMN · Motion capture | prediction error (x10^-2): 30.0 -> 29.6 | Improved |
| Increase estimation step k from 0 to 2, then larger | RF, EGNN, GMN · 5 datasets | prediction error | Mixed |
| Apply NC (k=2) to EqMotion for multi-step prediction | EqMotion · MD17 Aspirin multi-step | ADE: 5.95 -> 4.74 | Improved |
| Apply NC (k=2) to EqMotion | EqMotion · MD17 Benzene multi-step | ADE: 1.18 -> 1.15 | Improved |
Closest papers by meaning
- SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases (ICLR 2024 · similarity 0.87)
- When Graph Neural Networks Meet Dynamic Mode Decomposition (ICLR 2025 · similarity 0.86)
- Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics (AAAI 2024 · similarity 0.86)
- PGODE: Towards High-quality System Dynamics Modeling (ICML 2024 · similarity 0.86)
- Learning system dynamics without forgetting (ICLR 2025 · similarity 0.85)
- State Space Models on Temporal Graphs: A First-Principles Study (NeurIPS 2024 · 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.
