Metraipolis › archive › dc_607d97649769

Learning a Prior-Data Fitted Network for Graph Foundation Models via Structural Causal Model Priors — arXiv:2610.38335

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38335
License (as archived)
CC0-1.0
Archived
2026-11-01T02:24:47.684Z
SHA-256 of the archived text
73f0ee3e6466e3f48359640708d4c920d300a47f62e968f73de93562e0cf2d63
Stable URL of this page
https://metraipolis.com/documento/dc_607d97649769

How to cite

Learning a Prior-Data Fitted Network for Graph Foundation Models via Structural Causal Model Priors — arXiv:2610.38335 — arXiv (en), https://arxiv.org/abs/2610.38335 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_607d97649769 (Metraipolis archive dc_607d97649769, sha256 73f0ee3e6466e3f48359640708d4c920d300a47f62e968f73de93562e0cf2d63)
BibTeX
@misc{dc607d97649769,
  title = {Learning a Prior-Data Fitted Network for Graph Foundation Models via Structural Causal Model Priors — arXiv:2610.38335},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38335},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_607d97649769; sha256 73f0ee3e6466e3f48359640708d4c920d300a47f62e968f73de93562e0cf2d63},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38335. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for learning transferable representations across different graphs and domains. However, existing GFMs face notable limitations, including limited pre-training scale or reliance on aligning with textual information in Large Language Models (LLMs). To overcome these limitations, recent studies have drawn inspiration from prior-data fitted networks (PFNs), which learn from large synthetic datasets and support multi-domain prediction backed by causal learning. However, existing graph PFNs encounter severe difficulties in modeling causal relationships within and across node and edge sets, generating diverse graph structures, and designing suitable architectures that can learn from complex synthetic datasets. To address these challenges, we propose **GSCM-PFN** (Graph SCM-based Prior-Data Fitted Network), a graph PFN pre-trained on synthetic data generated from an SCM-based prior that jointly models nodes and graph topology. Specifically, we (1) design a joint feature-edge-label structural causal model (SCM) to guide synthetic graph generation and capture causal relationships within and across node and edge sets; (2) introduce prior-guided node-edge dependency modeling to instantiate diverse graph generation strategies, and prove that our SCM-based generation prior is more expressive than existing priors; and (3) propose a feature-permutation-invariant dual-path graph network with theoretical guarantees for learning from diverse synthetic graphs. Experiments on 23 real-world benchmarks show that GSCM-PFN outperforms both conventional GFMs and PFN-based GFMs, without utilizing real-world graph data for pre-training. Code: this https URL

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/2610.38335 — 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 2026-11-01T02:12:44.121Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).