Hugging Face Daily Papers · · 4 min read

Topology-Preserving Neural Operator Learning via Hodge Decomposition

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

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 <a href=\"https://github.com/ContinuumCoder/Hodge-Spectral-Duality\" rel=\"nofollow\">https://github.com/ContinuumCoder/Hodge-Spectral-Duality</a>.</p>\n","updatedAt":"2026-05-15T02:16:28.906Z","author":{"_id":"69b322027c89a6c6ac5e2474","avatarUrl":"/avatars/811a981d2c59e28f67c3afe6b5c2961e.svg","fullname":"Tao Zhong","name":"n3il666","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8732939958572388},"editors":["n3il666"],"editorAvatarUrls":["/avatars/811a981d2c59e28f67c3afe6b5c2961e.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.13834","authors":[{"_id":"6a053cb8b1a8cbabc9f087d2","name":"Dongzhe Zheng","hidden":false},{"_id":"6a053cb8b1a8cbabc9f087d3","name":"Tao Zhong","hidden":false},{"_id":"6a053cb8b1a8cbabc9f087d4","name":"Christine Allen-Blanchette","hidden":false}],"publishedAt":"2026-05-13T00:00:00.000Z","submittedOnDailyAt":"2026-05-15T00:00:00.000Z","title":"Topology-Preserving Neural Operator Learning via Hodge Decomposition","submittedOnDailyBy":{"_id":"69b322027c89a6c6ac5e2474","avatarUrl":"/avatars/811a981d2c59e28f67c3afe6b5c2961e.svg","isPro":false,"fullname":"Tao Zhong","user":"n3il666","type":"user","name":"n3il666"},"summary":"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","upvotes":3,"discussionId":"6a053cb9b1a8cbabc9f087d5","githubRepo":"https://github.com/ContinuumCoder/Hodge-Spectral-Duality","githubRepoAddedBy":"user","ai_summary":"Physical field equations on geometric meshes are analyzed through Hodge theory to develop a hybrid Eulerian-Lagrangian architecture that improves accuracy and efficiency by separating topological and geometric components.","ai_keywords":["Hodge orthogonality","spectral interference","topological degrees of freedom","geometric dynamics","operator-level decomposition","Hodge Spectral Duality","discrete differential forms","orthogonal auxiliary ambient space","geometric graphs","physical invariants"],"githubStars":2,"organization":{"_id":"64374111a701a7e744c02b0e","name":"princetonu","fullname":"Princeton University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/b3xXusq8Zz3ej8Z6fRTSZ.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"69b322027c89a6c6ac5e2474","avatarUrl":"/avatars/811a981d2c59e28f67c3afe6b5c2961e.svg","isPro":false,"fullname":"Tao Zhong","user":"n3il666","type":"user"},{"_id":"698c80f218b4ba9199a62155","avatarUrl":"/avatars/30da9abe1d99bfb9047b50fde6f8ff59.svg","isPro":false,"fullname":"Dongzhe Zheng","user":"DenzelZheng","type":"user"},{"_id":"63996725f123767aa2e46283","avatarUrl":"/avatars/3acd1390c6dba96d712765d302eb33e3.svg","isPro":false,"fullname":"Alan","user":"hiyata","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"64374111a701a7e744c02b0e","name":"princetonu","fullname":"Princeton University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/b3xXusq8Zz3ej8Z6fRTSZ.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.13834.md"}">
Papers
arxiv:2605.13834

Topology-Preserving Neural Operator Learning via Hodge Decomposition

Published on May 13
· Submitted by
Tao Zhong
on May 15
Authors:
,
,

Abstract

Physical field equations on geometric meshes are analyzed through Hodge theory to develop a hybrid Eulerian-Lagrangian architecture that improves accuracy and efficiency by separating topological and geometric components.

AI-generated summary

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

Community

Paper submitter about 23 hours ago

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.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.13834
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.13834 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.13834 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.13834 in a Space README.md to link it from this page.

Collections including this paper 1

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers