Metraipolis › archive › dc_bcc60875747d
Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks — arXiv:2609.19915
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19915
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T04:08:49.044Z
- SHA-256 of the archived text
5804a3fded8229374bc67526a59c02611aaec3b590f59538a23eed0223dcd0d9- Stable URL of this page
https://metraipolis.com/documento/dc_bcc60875747d
How to cite
Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks — arXiv:2609.19915 — arXiv (en), https://arxiv.org/abs/2609.19915 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcc60875747d (Metraipolis archive dc_bcc60875747d, sha256 5804a3fded8229374bc67526a59c02611aaec3b590f59538a23eed0223dcd0d9)
BibTeX
@misc{dcbcc60875747d,
title = {Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks — arXiv:2609.19915},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19915},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcc60875747d; sha256 5804a3fded8229374bc67526a59c02611aaec3b590f59538a23eed0223dcd0d9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19915. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Amortizing physics-informed neural networks (PINNs) across related PDEs requires describing each equation to a reusable solver. Coefficient vectors encode numerical parameters in predefined slots, leaving operator and cross-field assignments implicit. We make these relationships explicit in an operator graph, with nodes for fields, derivatives, terms, and residuals and coefficients retained as term attributes. A graph hypernetwork generates diagonal codes that initialize a meta-trained factorized PINN for each target equation. Meta-training and target-specific adaptation use governing equations and prescribed conditions without solution labels. We compare coefficient-vector, DeepSets-based term-set, and graph conditioning by solution accuracy within a fixed adaptation budget. In scalar convection-diffusion-reaction problems, both term-based descriptors improve high-reaction accuracy, with similar performance. In two-field Fisher-KPP, meta-training sees uncoupled and one-way systems; after 3,000 adaptation steps on unseen two-way coupling, the graph's mean final error is 35.7% below the term set and 67.7% below the coefficient vector. In a fixed-structure capacitively coupled plasma model, the coefficient vector performs best. These results support extending coefficient conditioning with explicit equation relationships for physics-based solver adaptation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.19915 — 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 2026-10-10T03:48:18.304Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).