Metraipolis › archive › dc_d67aff672194

Sheaf-MPNN: A Library for Sheaf Neural Networks as Message Passing — arXiv:2611.04670

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04670
License (as archived)
CC0-1.0
Archived
2026-11-04T18:54:11.105Z
SHA-256 of the archived text
d8f9388a17e795c03ed5a4c581e2b0f37f4f257e93f55c716cae5faf47baf37f
Stable URL of this page
https://metraipolis.com/documento/dc_d67aff672194

How to cite

Sheaf-MPNN: A Library for Sheaf Neural Networks as Message Passing — arXiv:2611.04670 — arXiv (en), https://arxiv.org/abs/2611.04670 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d67aff672194 (Metraipolis archive dc_d67aff672194, sha256 d8f9388a17e795c03ed5a4c581e2b0f37f4f257e93f55c716cae5faf47baf37f)
BibTeX
@misc{dcd67aff672194,
  title = {Sheaf-MPNN: A Library for Sheaf Neural Networks as Message Passing — arXiv:2611.04670},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04670},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d67aff672194; sha256 d8f9388a17e795c03ed5a4c581e2b0f37f4f257e93f55c716cae5faf47baf37f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04670. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Standard Graph Neural Networks (GNNs) implicitly assume that neighboring nodes share the same feature space, which contributes to oversmoothing and poor performance on heterophilic graphs. Sheaf Neural Networks (SNNs) remove this assumption by giving each node and edge its own vector space and learning restriction maps that transform features as they move between neighbors. These maps define a sheaf Laplacian that drives diffusion over the graph, but existing implementations often assemble it explicitly as a global sparse block matrix, which adds memory and computational overhead and can hinder scalability. In this paper, we introduce Sheaf-MPNN, a PyTorch Geometric library that reformulates sheaf diffusion as local incidence-wise transport and aggregation, eliminating the need to construct the global Laplacian. Sheaf-MPNN implements fifteen families of SNNs under a unified message-passing framework, each supporting both homogeneous and heterogeneous graphs, and directed and undirected settings, with diagonal, general, orthogonal, and low-rank restriction maps and attention-based predictors. We further provide a unified benchmarking suite covering node- and graph-level tasks, heterogeneous graph learning, and computational efficiency, enabling systematic and reproducible comparisons across architectures. We establish theoretical equivalence between these message-passing formulations and their original counterparts and identify the architectural mechanisms needed to preserve their propagation dynamics. This unified perspective provides a principled foundation for implementing, comparing, and extending sheaf-based architectures within standard graph learning frameworks. Source code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.04670 — 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 2026-11-04T18:35:37.454Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).