Metraipolis › archive › dc_b80bba18fe74

Toward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach — arXiv:2610.02881

Source
arXiv
Original
https://arxiv.org/abs/2610.02881
License (as archived)
CC0-1.0
Archived
2026-10-05T23:09:58.746Z
SHA-256 of the archived text
6b7d06ba89e04fda05983ee863cd3a32954ef72788abb0a187f675da18509ca7
Stable URL of this page
https://metraipolis.com/documento/dc_b80bba18fe74

How to cite

Toward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach — arXiv:2610.02881 — arXiv, https://arxiv.org/abs/2610.02881 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b80bba18fe74 (Metraipolis archive dc_b80bba18fe74, sha256 6b7d06ba89e04fda05983ee863cd3a32954ef72788abb0a187f675da18509ca7)
BibTeX
@misc{dcb80bba18fe74,
  title = {Toward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach — arXiv:2610.02881},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02881},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b80bba18fe74; sha256 6b7d06ba89e04fda05983ee863cd3a32954ef72788abb0a187f675da18509ca7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02881. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal graph foundation models (MGFMs) seek to learn generalizable representations from large-scale graphs with heterogeneous node modalities. However, real-world Multimodal-Attributed Graphs (MAGs) often contain incomplete node attributes, limiting the scale and diversity of available pretraining corpora. Besides, existing MGFMs primarily incorporate graph topology as structural context, overlooking its role in guiding multimodal binding and shaping a unified representation space. To address these challenges, we propose GraphBind, a topology-driven approach that uses graph topology to bind rich modality information into a unified shared space. GraphBind is motivated by the stability of graph topology, which provides structural references and complementary semantic information for multimodal binding. Concretely, GraphBind uses topology to organize self semantics and reliable neighborhood semantics into a global shared space that integrates structure and semantics, and adapts this space to discriminative and generative tasks through lightweight interfaces. Extensive experiments against 11 representative baselines demonstrate that GraphBind achieves leading performance on both discriminative and generative tasks, with relative improvements of up to 28.1% over the strongest baseline.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.02881 — 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 2026-10-05T23:01:38.647Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).