Research map / Graph learning / GNN architectures
Error-Driven Graph Augmentation for Mesh-Based PDE Surrogates
Xuan Minh Vuong Nguyen, Nissrine Akkari, Fabien Casenave, Jonathan Viquerat, Elie Hachem
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 error-guided augmentation instead of best non-error-guided equal-budget edges (ablation) | MiSe-GNN · 2D profile | macro RRMSE: 0.0368 -> 0.0295 | Improved |
| use error-guided augmentation instead of best equal-budget control (ablation) | MiSe-GNN · 2D MultiScHypEl | macro RRMSE: 0.0242 -> 0.0224 | Improved |
| scale capacity from 10 MP/32 to 15 MP/80 (ablation) | MiSe-GNN · 2D profile | macro RRMSE: 0.0431 -> 0.0372 | Improved |
| add DID input features (ablation) | MiSe-GNN (15/80) · 2D profile | macro RRMSE: 0.0372 -> 0.0315 | Improved |
| add Sinus and Sph encodings to DID (ablation) | MiSe-GNN (15/80) · 2D profile | macro RRMSE: 0.0315 -> 0.0295 | Improved |
| add Sinus and Sph encodings to DID (ablation) | MiSe-GNN (15/80) · 2D profile | Pressure RRMSE: 0.02123 -> 0.02543 | Hurt |
| add OurFeat features to DID (ablation) | MiSe-GNN (15/80) · 2D MultiScHypEl | macro RRMSE: 0.0251 -> 0.0224 | Improved |
| give MGN and MGN Tree the OurFeat+DID features (stronger inputs do not close the gap) (ablation) | MGN / MGN Tree · 2D MultiScHypEl | macro RRMSE: 0.0269 and 0.0261 vs 0.0224 for MiSe-GNN | No clear effect |
| add hierarchical tree rewiring to MGN (ablation) | MGN · 2D profile (DID+Sinus+Sph) | macro RRMSE: 0.0356 -> 0.0376 | Hurt |
| add error-guided augmentation to MGN | MGN · 2D MultiScHypEl (10/32) | u1 RRMSE: 0.0419 -> 0.0185 | Improved |
| add error-guided augmentation to MGN | MGN · 2D profile (10/32) | Pressure RRMSE: 0.0624 -> 0.0290 | Improved |
Closest papers by meaning
- PIORF: Physics-Informed Ollivier-Ricci Flow for Long–Range Interactions in Mesh Graph Neural Networks (ICLR 2025 · similarity 0.88)
- G-Adaptivity: optimised graph-based mesh relocation for finite element methods (ICML 2025 · similarity 0.88)
- PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems (ICLR 2025 · similarity 0.86)
- EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutions (ICML 2025 · similarity 0.86)
- UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss (NeurIPS 2025 · similarity 0.86)
- Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networks (ICLR 2025 · similarity 0.86)
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.
