{
  "abstract": "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",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "Laurynas Varnas"
    },
    {
      "name": "Julien Herrmann"
    },
    {
      "name": "Alexander Heinlein"
    },
    {
      "name": "Serge Gratton"
    },
    {
      "name": "Alena Kopaničáková"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9hnd46wjcctey.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.22575",
  "fulltext_url": null,
  "id": "9hnd46wjcctey",
  "issns": [],
  "landing_url": "https://hal.science/hal-05753812v1",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "hal",
      "0.info"
    ],
    [
      "hal",
      "0.math"
    ],
    [
      "hal",
      "1.info.info-lg"
    ],
    [
      "hal",
      "1.math.math-na"
    ],
    [
      "openalex",
      "1702|Advanced Graph Neural Networks"
    ]
  ],
  "openalex": "W7204184930",
  "pdf_url": "https://hal.science/hal-05753812/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9hnd46wjcctey.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:36Z",
      "native_id": "hal-05753812",
      "source": "hal",
      "url": "https://hal.science/hal-05753812v1"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "hal:1.math.math-na",
      "subfield": "numerical-analysis"
    }
  ],
  "title": "Two-level domain-decomposition AdaGrad method for scalable training of graph neural networks",
  "title_text": "Two-level domain-decomposition AdaGrad method for scalable training of graph neural networks",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:36Z",
  "url": "https://research.draconitic.com/paper/9hnd46wjcctey",
  "venue": "HAL",
  "versions": []
}