Metraipolis › archive › dc_cf083ed488a0
Two-level domain-decomposition AdaGrad method for scalable training of graph neural networks — arXiv:2608.22575
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22575
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T08:27:36.245Z
- SHA-256 of the archived text
ce61d50c23a0348ddfaf23f6816e188952b4d7c21b71c0d0833454277a6355cf- Stable URL of this page
https://metraipolis.com/documento/dc_cf083ed488a0
How to cite
Two-level domain-decomposition AdaGrad method for scalable training of graph neural networks — arXiv:2608.22575 — arXiv (en), https://arxiv.org/abs/2608.22575 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf083ed488a0 (Metraipolis archive dc_cf083ed488a0, sha256 ce61d50c23a0348ddfaf23f6816e188952b4d7c21b71c0d0833454277a6355cf)
BibTeX
@misc{dccf083ed488a0,
title = {Two-level domain-decomposition AdaGrad method for scalable training of graph neural networks — arXiv:2608.22575},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22575},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf083ed488a0; sha256 ce61d50c23a0348ddfaf23f6816e188952b4d7c21b71c0d0833454277a6355cf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22575. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Graph neural networks (GNNs) have emerged as a powerful framework for learning from graph-structured data. However, their efficient training remains challenging, particularly in distributed computing environments. This challenge arises from the use of message passing, which couples all graph nodes, leading to expensive optimization steps, high memory requirements, and substantial communication overhead. To alleviate these limitations, we propose a novel domain-decomposition (DD) variant of AG2m, an AdaGrad method enhanced with second-order curvature information and momentum, denoted by DD-AG2m. The proposed DD-AG2m alternates between AG2m optimization on the original (global) graph and AG2m optimization on the partitioned graphs. To incorporate global information at reduced cost, we further introduce a two-level variant (2DD-AG2m) that performs global optimization steps on a coarse graph obtained by randomly subsampling nodes within each subdomain. Numerical experiments spanning graph classification, node-level regression, and spatiotemporal forecasting tasks demonstrate that the proposed DD methods reduce the computational cost required to achieve the same predictive performance by a factor of 4-8. Moreover, for the fixed computational cost, they improve the predictive performance of GNNs by up to 22% compared with the baseline AG2m. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-25 in math.NA). Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.22575 — 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 2026-10-18T08:27:23.848Z dalla pagina https://arxiv.org/catchup/math.NA/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).