Metraipolis › archive › dc_49f2f8d0f55b
Green-Routed Neural Operators:\\Physics Determines Where the Network Reads — arXiv:2610.05337
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05337
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:26:49.637Z
- SHA-256 of the archived text
c66ff5fe4598dd3fb5d4065584cda54a0bf5be033b475a21a9223da55c1326bc- Stable URL of this page
https://metraipolis.com/documento/dc_49f2f8d0f55b
How to cite
Green-Routed Neural Operators:\\Physics Determines Where the Network Reads — arXiv:2610.05337 — arXiv, https://arxiv.org/abs/2610.05337 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49f2f8d0f55b (Metraipolis archive dc_49f2f8d0f55b, sha256 c66ff5fe4598dd3fb5d4065584cda54a0bf5be033b475a21a9223da55c1326bc)
BibTeX
@misc{dc49f2f8d0f55b,
title = {Green-Routed Neural Operators:Physics Determines Where the Network Reads — arXiv:2610.05337},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05337},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49f2f8d0f55b; sha256 c66ff5fe4598dd3fb5d4065584cda54a0bf5be033b475a21a9223da55c1326bc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05337. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We identify a mismatch between the physical role of transport fields in many PDEs and their usual role in neural operators: PDEs use them to select read coordinates, whereas neural operators typically treat them only as input values. We address this mismatch with the Green-Routed Neural Operator (GRNO), which uses the governing equation to determine where latent features are sampled. A parameter-free equation adapter evaluates the diagnostic relation and constructs a departure map whose values are the read coordinates. A multiscale encoder-decoder combines centered and routed reads of latent features to learn the complete finite-time update. Across five two- and three-dimensional PDE systems, GRNO achieves the lowest mean final relative $L^2$ error on four under 40-step autoregressive evaluation and remains competitive on Keller-Segel. Fixed-weight route interventions reveal strong dependence on direction and spatial alignment in four systems, with weak dependence in Keller-Segel. In independently trained ablations, GRNO achieves lower mean errors than variants that supply the transport field only as an input feature, substitute a learned displacement for the equation-specified route, or apply the route with a spatial misalignment, across all five systems. It also substantially outperforms directly advecting the physical state and learning the remaining update, indicating that equation-specified read coordinates provide an effective structural prior for long-horizon PDE forecasting. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.05337 — 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 2026-10-06T05:24:05.999Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).