Metraipolis › archive › dc_835fd612ca49
RBF-GNN: Rational Basis Functions for Pseudo-Coordinate based Graph Convolutions — arXiv:2609.37015
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37015
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:40:48.426Z
- SHA-256 of the archived text
3bd205530df1d7d02264af5ed72bde32914d2256e6e2311350d8ff8563e85667- Stable URL of this page
https://metraipolis.com/documento/dc_835fd612ca49
How to cite
RBF-GNN: Rational Basis Functions for Pseudo-Coordinate based Graph Convolutions — arXiv:2609.37015 — arXiv (en), https://arxiv.org/abs/2609.37015 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_835fd612ca49 (Metraipolis archive dc_835fd612ca49, sha256 3bd205530df1d7d02264af5ed72bde32914d2256e6e2311350d8ff8563e85667)
BibTeX
@misc{dc835fd612ca49,
title = {RBF-GNN: Rational Basis Functions for Pseudo-Coordinate based Graph Convolutions — arXiv:2609.37015},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37015},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_835fd612ca49; sha256 3bd205530df1d7d02264af5ed72bde32914d2256e6e2311350d8ff8563e85667},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37015. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We propose RBF-GNN, a new pseudo-coordinate based graph neural network architecture that takes into account Euclidean, spherical or angular coordinates and uses them to induce a powerful spatial inductive bias. Similar in architecture to SplineCNN, we improve upon the latter by replacing the less efficient sparse-activation based B-splines whose number grows exponentially with dimension by rational Padé basis functions. For effective training we propose a spline-subspace initialization and a variance-preserving weight rescaling. Experimentally, we evaluate on a number of popular neural network architectures that use SplineCNNs. We replace only the SplineCNNs with RBF-GNN. We achieve improved results, including on semantic keypoint matching, shape matching, event based camera computer vision tasks. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.37015 — 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 2026-10-07T18:04:24.799Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).