Metraipolis › archive › dc_66abec9c30ec
Training Graph Foundation Models on The Web Graph — arXiv:2609.30894
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30894
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T01:38:25.442Z
- SHA-256 of the archived text
2e922ac413ad8418ddf706a132d6f0bfcc692bbce65c77857f90bf374ea8becc- Stable URL of this page
https://metraipolis.com/documento/dc_66abec9c30ec
How to cite
Training Graph Foundation Models on The Web Graph — arXiv:2609.30894 — arXiv (en), https://arxiv.org/abs/2609.30894 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_66abec9c30ec (Metraipolis archive dc_66abec9c30ec, sha256 2e922ac413ad8418ddf706a132d6f0bfcc692bbce65c77857f90bf374ea8becc)
BibTeX
@misc{dc66abec9c30ec,
title = {Training Graph Foundation Models on The Web Graph — arXiv:2609.30894},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30894},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_66abec9c30ec; sha256 2e922ac413ad8418ddf706a132d6f0bfcc692bbce65c77857f90bf374ea8becc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30894. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce Acacia, a graph foundation model, trained on the web graph. Acacia (i) supports arbitrary feature dimensionalities and semantics without additional training, (ii) supports a wide range of tasks, including node classification, link prediction, node clustering, and graph generation, without additional training, (iii) has in-context learning capabilities, and (iv) does not rely on pretrained LLMs. In particular, existing graph foundation models often require training additional classification heads or feature projectors to accommodate new graphs or new labels, whereas Acacia does not. Moreover, existing graph foundation models often gain their capabilities by being stitched together with pretrained LLMs, whereas Acacia is trained from scratch using only the Common Crawl web graph. This is also an important result because it provides evidence that graph models can acquire emergent capabilities from scratch like LLMs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.30894 — 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 2026-10-08T01:12:14.306Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).