Metraipolis › archive › dc_52d500ea4b0e
Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs — arXiv:2608.28853
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28853
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:47:20.080Z
- SHA-256 of the archived text
7a8a866b32ca53a4b62e26b65c49ce547b4e5c05c2ccf79a245cf12de7c8ab22- Stable URL of this page
https://metraipolis.com/documento/dc_52d500ea4b0e
How to cite
Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs — arXiv:2608.28853 — arXiv (en), https://arxiv.org/abs/2608.28853 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_52d500ea4b0e (Metraipolis archive dc_52d500ea4b0e, sha256 7a8a866b32ca53a4b62e26b65c49ce547b4e5c05c2ccf79a245cf12de7c8ab22)
BibTeX
@misc{dc52d500ea4b0e,
title = {Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs — arXiv:2608.28853},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28853},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_52d500ea4b0e; sha256 7a8a866b32ca53a4b62e26b65c49ce547b4e5c05c2ccf79a245cf12de7c8ab22},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28853. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Equivariant graph neural networks provide a principled way to model geometric systems, but efficient first-order architectures remain limited in how vector information can be transformed as it moves across a graph. We introduce \textsc{ESNN}, an Equivariant Sheaf Neural Network that enriches this interaction by learning directed, matrix-valued transport between neighboring vector features while preserving exact Euclidean equivariance. Rather than increasing the order of the representation, ESNN keeps scalar and vector features first-order and places the additional geometric flexibility in the edge transport itself. We characterize this transport theoretically, showing that when relative displacement is the only covariant geometric input, every linear $O(n)$-equivariant map decomposes into independent radial and tangential components, while learned covariant features enable richer feature-conditioned transformations. We also introduce controlled symmetry relaxation for systems with a preferred ambient direction, which may be prescribed or inferred from data while recovering full $E(n)$-equivariance when the directional pathway is inactive. Across particle dynamics, mesh-based simulation, point-cloud classification, and molecular property prediction, ESNN improves dynamics prediction, recovers the gravity axis when symmetry is broken, yields substantial gains on selected mesh tasks and long-horizon rollouts, and remains robust to unseen rotations. These results show that learning how geometric information is transported across edges offers a complementary route to expressive equivariant message passing without requiring higher-order representations.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28853 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:28:26.694Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).