Metraipolis › archive › dc_2e12bac65748

Towards Unified Multimodal Graph Foundation Model: A Bridge-Router-Adapter Based Approach — arXiv:2609.06668

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06668
License (as archived)
CC0-1.0
Archived
2026-10-16T13:57:16.667Z
SHA-256 of the archived text
8df2c7112d31f09662bd9bbea4089a618142eec1a478e5d973408cfd727e5648
Stable URL of this page
https://metraipolis.com/documento/dc_2e12bac65748

How to cite

Towards Unified Multimodal Graph Foundation Model: A Bridge-Router-Adapter Based Approach — arXiv:2609.06668 — arXiv (en), https://arxiv.org/abs/2609.06668 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e12bac65748 (Metraipolis archive dc_2e12bac65748, sha256 8df2c7112d31f09662bd9bbea4089a618142eec1a478e5d973408cfd727e5648)
BibTeX
@misc{dc2e12bac65748,
  title = {Towards Unified Multimodal Graph Foundation Model: A Bridge-Router-Adapter Based Approach — arXiv:2609.06668},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06668},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e12bac65748; sha256 8df2c7112d31f09662bd9bbea4089a618142eec1a478e5d973408cfd727e5648},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06668. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal graphs couple node attributes in different modalities, such as text and images, with relational structure, enabling topological structure and cross-modality attributes to be modeled jointly. Multimodal graph foundation models seek unified representations from such data that transfer across different graph domains and downstream tasks. However, existing methods exhibit two fundamental limitations. (1) Cross-Scope Context Entanglement. They merge scope-specific graph contexts into a unified representation, obscuring their distinctions during multimodal construction. (2) Scope-Ignorant Modality Routing. They route modalities within a fixed graph scope, overlooking how modality relevance varies across neighborhood ranges. To address these challenges, we propose BRAIN, a unified model that focuses on graph context that combines neighborhood scope with modality composition. BRAIN comprises a scope-conditioned Bridge that combines structural information spanning local-to-global neighborhood scopes with different modality compositions; a hierarchical Router that estimates the relevance between the scope and the task, and selects compositions separately within each scope, allowing modality utility to vary with graph range; and a lightweight residual Adapter that further specializes the routed embedding for downstream prediction. BRAIN is trained through multi-graph pretraining followed by task-specific adaptation. Experiments across nine datasets and four task families demonstrate its broad effectiveness, improving node-classification and link-prediction performance by up to 4.73% relative to the strongest baseline, while achieving an average relative improvement of 14.72% across four graph-to-text and two graph-to-image metrics.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.06668 — 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 2026-10-16T13:39:42.905Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).