Research map / Graph learning / Knowledge and temporal graphs
HOPE: High-order Graph ODE For Modeling Interacting Dynamics
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 |
|---|---|---|---|
| Add second-order graph ODE (momentum-style) instead of first-order ODE for nodes and edges | graph ODE generative model · COVID-19 / Social Network / Spring Oscillator | MAE: avg MAE 169.9 vs 175.1 (CG-ODE) on COVID-19 | Helped |
| Remove second-order derivative term from graph ODE (ablation) | HOPE · Social Network (avg of 10/20/40) | MAE: 0.1876 without vs 0.1786 full | Helped |
| Remove edge evolution neural ODE (ablation) | HOPE · Social Network (avg of 10/20/40) | MAE: 0.2151 without vs 0.1786 full | Helped |
| Remove first-order spatial convolution from encoder (ablation) | HOPE encoder · Social Network (avg of 10/20/40) | MAE: 0.2260 without vs 0.1786 full | Helped |
| Remove second-order spectral convolution from encoder (ablation) | HOPE encoder · Social Network (avg of 10/20/40) | MAE: 0.1840 without vs 0.1786 full | Helped |
| Remove first-order derivative term (gamma term) from graph ODE (ablation) | HOPE · Social Network (avg of 10/20/40) | MAE: 0.2037 without vs 0.1786 full | Helped |
| Use a single-layer twin graph encoder (K=1) instead of deeper stacks (ablation) | HOPE encoder · Social Network sensitivity | prediction performance (MAPE/RMSE) | Mixed |
| Second-order ODE vs CG-ODE at equal error tolerance | graph ODE solver · COVID-19 and Social Network NFE | NFE | Helped |
Closest papers by meaning
- PGODE: Towards High-quality System Dynamics Modeling (ICML 2024 · similarity 0.90)
- CSG-ODE: ControlSynth Graph ODE For Modeling Complex Evolution of Dynamic Graphs (ICML 2025 · similarity 0.89)
- Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics (AAAI 2024 · similarity 0.88)
- Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems (NeurIPS 2026 · similarity 0.87)
- A Graph Dynamics Prior for Relational Inference (AAAI 2024 · similarity 0.87)
- SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases (ICLR 2024 · similarity 0.87)
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.