Metraipolis › archive › dc_df0b6d9db129

Clifford Sheaf Neural Networks — arXiv:2610.01322

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01322
License (as archived)
CC0-1.0
Archived
2026-10-06T15:33:47.636Z
SHA-256 of the archived text
d99710de5f509478f9b7ef0583e25076f773e49a7f183aea85c08b44f1d6ee2a
Stable URL of this page
https://metraipolis.com/documento/dc_df0b6d9db129

How to cite

Clifford Sheaf Neural Networks — arXiv:2610.01322 — arXiv (en), https://arxiv.org/abs/2610.01322 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df0b6d9db129 (Metraipolis archive dc_df0b6d9db129, sha256 d99710de5f509478f9b7ef0583e25076f773e49a7f183aea85c08b44f1d6ee2a)
BibTeX
@misc{dcdf0b6d9db129,
  title = {Clifford Sheaf Neural Networks — arXiv:2610.01322},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01322},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df0b6d9db129; sha256 d99710de5f509478f9b7ef0583e25076f773e49a7f183aea85c08b44f1d6ee2a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01322. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce the Clifford Sheaf Neural Network (CSNN), an equivariant sheaf neural network for geometric graphs that places a Clifford algebra on each stalk of a cellular sheaf and transports multivector features along edges. The canonical choice of restriction map for sheaves with algebra-valued stalks is algebra homomorphism. Adding the constraint of equivariance, the naive choice becomes versor conjugation. However, versor conjugation is expressively weak, so we drop algebra homomorphism and arrive at the K-term sandwich. The resulting sheaf Laplacian is positive semidefinite by construction, needs no versor constraint, and still mixes grades. Our main contribution characterizes the resulting family of restriction maps along three axes: which grades a map couples, how much of the endomorphism space it reaches, and how well it is conditioned. The K-term sandwich spans half of the endomorphism space, and in Cl(3, 0, 0) it corresponds to the maps that commute with the central pseudoscalar. The number of terms controls expressivity. CSNN is the reversion member, a first-order model by construction and the grade-mixing corner of this family, developed as a sheaf construction for graph-level equivariant regression.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in stat.ML).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.01322 — 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 2026-10-06T15:12:55.901Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).