Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.13834 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917549015302144 |
|---|---|
| author | Zheng, Dongzhe Zhong, Tao Allen-Blanchette, Christine |
| author_facet | Zheng, Dongzhe Zhong, Tao Allen-Blanchette, Christine |
| contents | In this paper, we study solution operators of physical field equations on geometric meshes from a function-space perspective. We reveal that Hodge orthogonality fundamentally resolves spectral interference by isolating unlearnable topological degrees of freedom from learnable geometric dynamics, enabling an additive approximation confined to structure-preserving subspaces. Building on Hodge theory and operator splitting, we derive a principled operator-level decomposition. The result is a Hybrid Eulerian-Lagrangian architecture with an algebraic-level inductive bias we call Hodge Spectral Duality (HSD). In our framework, we use discrete differential forms to capture topology-dominated components and an orthogonal auxiliary ambient space to represent complex local dynamics. Our method achieves superior accuracy and efficiency on geometric graphs with enhanced fidelity to physical invariants. Our code is available at https://github.com/ContinuumCoder/Hodge-Spectral-Duality |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13834 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Topology-Preserving Neural Operator Learning via Hodge Decomposition Zheng, Dongzhe Zhong, Tao Allen-Blanchette, Christine Machine Learning Artificial Intelligence Computational Geometry In this paper, we study solution operators of physical field equations on geometric meshes from a function-space perspective. We reveal that Hodge orthogonality fundamentally resolves spectral interference by isolating unlearnable topological degrees of freedom from learnable geometric dynamics, enabling an additive approximation confined to structure-preserving subspaces. Building on Hodge theory and operator splitting, we derive a principled operator-level decomposition. The result is a Hybrid Eulerian-Lagrangian architecture with an algebraic-level inductive bias we call Hodge Spectral Duality (HSD). In our framework, we use discrete differential forms to capture topology-dominated components and an orthogonal auxiliary ambient space to represent complex local dynamics. Our method achieves superior accuracy and efficiency on geometric graphs with enhanced fidelity to physical invariants. Our code is available at https://github.com/ContinuumCoder/Hodge-Spectral-Duality |
| title | Topology-Preserving Neural Operator Learning via Hodge Decomposition |
| topic | Machine Learning Artificial Intelligence Computational Geometry |
| url | https://arxiv.org/abs/2605.13834 |