Metraipolis › archive › dc_6e20cd844960

A Learnable Multigrid Framework via Graph Convolutions — arXiv:2608.29082

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29082
License (as archived)
CC0-1.0
Archived
2026-10-17T09:28:23.787Z
SHA-256 of the archived text
2564dc8e636e9cc0d35749bed0b06886fcd0abfac82087907b7c287a50b56f30
Stable URL of this page
https://metraipolis.com/documento/dc_6e20cd844960

How to cite

A Learnable Multigrid Framework via Graph Convolutions — arXiv:2608.29082 — arXiv (en), https://arxiv.org/abs/2608.29082 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6e20cd844960 (Metraipolis archive dc_6e20cd844960, sha256 2564dc8e636e9cc0d35749bed0b06886fcd0abfac82087907b7c287a50b56f30)
BibTeX
@misc{dc6e20cd844960,
  title = {A Learnable Multigrid Framework via Graph Convolutions — arXiv:2608.29082},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29082},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6e20cd844960; sha256 2564dc8e636e9cc0d35749bed0b06886fcd0abfac82087907b7c287a50b56f30},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29082. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper presents a novel framework that integrates learnable graph convolutions with the geometric multigrid method for solving partial differential equations (PDEs). The discretization of PDEs is first represented as a graph structure, enabling the application of graph convolutions to enhance the multigrid performance. By incorporating graph convolutions into the multigrid components such as smoothing and inter-grid transfer operators, we develop a learnable multigrid that can adaptively optimize its performance based on the underlying problem characteristics. In this framework, the graph convolutions are embedded directly within the multigrid cycle, effectively transforming the entire multigrid solver into a specialized neural network architecture, rather than combining a classical solver with surrogate models. The learnable multigrid framework is lightweight in terms of parameter count and requires minimal training effort to achieve good performance. Numerical experiments demonstrate the effectiveness of the proposed approach in solving some challenging problems, showing improved convergence rates compared to traditional multigrid methods. The generalizability of the learned parameters across different problem settings, including varying source terms, coefficients, geometries, and mesh sizes, is also investigated with proper weight-sharing and transfer-learning strategies.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-01 in math.NA).
Categorie arXiv: Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2608.29082 — 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 2026-10-17T08:59:54.345Z dalla pagina https://arxiv.org/catchup/math.NA/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).