Metraipolis › archive › dc_aef1061dfc98

Pre-training with Graph Transformers — arXiv:2609.13844

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13844
License (as archived)
CC0-1.0
Archived
2026-10-16T00:10:30.388Z
SHA-256 of the archived text
302f4ba00fb3e4c3371c9d4e588956bf45d4481ac706ad1af264876815000470
Stable URL of this page
https://metraipolis.com/documento/dc_aef1061dfc98

How to cite

Pre-training with Graph Transformers — arXiv:2609.13844 — arXiv (en), https://arxiv.org/abs/2609.13844 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aef1061dfc98 (Metraipolis archive dc_aef1061dfc98, sha256 302f4ba00fb3e4c3371c9d4e588956bf45d4481ac706ad1af264876815000470)
BibTeX
@misc{dcaef1061dfc98,
  title = {Pre-training with Graph Transformers — arXiv:2609.13844},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13844},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aef1061dfc98; sha256 302f4ba00fb3e4c3371c9d4e588956bf45d4481ac706ad1af264876815000470},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13844. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This article investigates pre-training strategies for graph transformers in the biochemistry domain. By conducting comprehensive experiments, the study reveals that supervised pre-training using computed properties as labels provides the highest performance gain on downstream tasks. The results also highlight the importance of constraining model capacity to mitigate overfitting in graph transformers.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.13844 — 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 2026-10-15T23:54:14.644Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).