Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Topology-Preserving Neural Operator Learning via Hodge Decomposition
Dongzhe Zheng, Tao Zhong, Christine Allen-Blanchette
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 commutator correction MLP C_theta (ablation) | HSD · Magnetostatics | MSE: 2.18 × 10^-4 -> 1.84 × 10^-4 | Improved |
| add commutator correction MLP C_theta (ablation) | HSD · External Aerodynamics | MSE: 1.17 × 10^-2 -> 1.08 × 10^-2 | Improved |
| add commutator correction MLP C_theta (ablation) | HSD · Toroidal Transport | MSE: 3.79 × 10^-4 -> 3.56 × 10^-4 | Improved |
| add orthogonal projection onto fiber complement (ablation) | HSD · External Aerodynamics | MSE: 1.45 × 10^-2 -> 1.08 × 10^-2 | Improved |
| add orthogonal projection onto fiber complement (ablation) | HSD · Magnetostatics | MSE: 2.20 × 10^-4 -> 1.84 × 10^-4 | Improved |
| add orthogonal projection onto fiber complement (ablation) | HSD · Toroidal Transport | MSE: 3.72 × 10^-4 -> 3.56 × 10^-4 | Improved |
| increase spectral modes from 64 to 256 (ablation) | HSD · Magnetostatics | MSE: 1.84 × 10^-4 -> 1.58 × 10^-4 | Improved |
| increase spectral modes from 64 to 256 (ablation) | HSD · External Aerodynamics | MSE: 1.08 × 10^-2 -> 8.99 × 10^-3 | Improved |
| increase spectral modes from 64 to 256 (ablation) | HSD · Toroidal Transport | MSE: 3.56 × 10^-4 -> 2.73 × 10^-4 | Improved |
| increase spectral modes from 64 to 128 (ablation) | HSD · Toroidal Transport | MSE: 3.56 × 10^-4 -> 2.80 × 10^-4 | Improved |
| replace FNO-3D with HSD (Hodge base + fiber branches) | FNO-3D · External Aerodynamics | MSE: 1.80 × 10^-2 -> 1.08 × 10^-2 | Improved |
| replace DeepONet with HSD | DeepONet · Magnetostatics | MSE: 2.89 × 10^-4 -> 1.84 × 10^-4 | Improved |
Closest papers by meaning
- Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving (ICLR 2026 · similarity 0.88)
- GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators (NeurIPS 2026 · similarity 0.85)
- Optimal deep learning of holomorphic operators between Banach spaces (NeurIPS 2024 · similarity 0.85)
- RIGNO: A Graph-based Framework For Robust And Accurate Operator Learning For PDEs On Arbitrary Domains (NeurIPS 2025 · similarity 0.85)
- A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics (ICLR 2025 · similarity 0.84)
- Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations (ICML 2025 · 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.
