Metraipolis › archive › dc_2bf988971d7b

Logic-Guided Graph Denoising Diffusion Models — arXiv:2610.23766

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23766
License (as archived)
CC0-1.0
Archived
2026-10-19T09:10:27.955Z
SHA-256 of the archived text
d6f262d421ba7e5d316ca228aa16940b58cadf54aeb82f958b3727437b38b5d4
Stable URL of this page
https://metraipolis.com/documento/dc_2bf988971d7b

How to cite

Logic-Guided Graph Denoising Diffusion Models — arXiv:2610.23766 — arXiv (en), https://arxiv.org/abs/2610.23766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bf988971d7b (Metraipolis archive dc_2bf988971d7b, sha256 d6f262d421ba7e5d316ca228aa16940b58cadf54aeb82f958b3727437b38b5d4)
BibTeX
@misc{dc2bf988971d7b,
  title = {Logic-Guided Graph Denoising Diffusion Models — arXiv:2610.23766},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23766},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bf988971d7b; sha256 d6f262d421ba7e5d316ca228aa16940b58cadf54aeb82f958b3727437b38b5d4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph diffusion models are competitive approaches for generating complex graph-structured data. However, when such distributions have strict structural constraints, diffusion models may fail to capture them exactly, resulting in the generation of invalid graphs. In this paper, we propose a method for grounding graph diffusion models in domain-specific knowledge via First Order Logic (FOL), leveraging its expressive and interpretable formalism to impose structural constraints on the generative process. We incorporate domain knowledge using classifier guidance, a technique that conditions the diffusion model's distribution on external variables to exert control over the sampled data. During the generative process, classifier guidance steers the denoising trajectory to optimize an objective function, which we define as a fuzzy and differentiable relaxation of the logical rules. Our methodology requires only the specification of constraints in FOL, whose satisfaction is encouraged at inference time to guide a pre-trained generative model. We evaluate our approach by comparing the unconditional generation of knowledge graphs with our logic-guided framework, which incorporates domain ontologies as structural constraints during inference. This approach significantly increases the proportion of generated graphs that satisfy the ontological constraints.

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/2610.23766 — 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 2026-10-19T09:06:29.572Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).