Metraipolis › archive › dc_f649d316fd02
SNACK: A Sequential Notation Framework for Probabilistic Graph Generation — arXiv:2610.19781
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19781
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:23:36.224Z
- SHA-256 of the archived text
58cedbfee4519f735308c59012963d02267782611760deedb18244de81b56044- Stable URL of this page
https://metraipolis.com/documento/dc_f649d316fd02
How to cite
SNACK: A Sequential Notation Framework for Probabilistic Graph Generation — arXiv:2610.19781 — arXiv (en), https://arxiv.org/abs/2610.19781 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f649d316fd02 (Metraipolis archive dc_f649d316fd02, sha256 58cedbfee4519f735308c59012963d02267782611760deedb18244de81b56044)
BibTeX
@misc{dcf649d316fd02,
title = {SNACK: A Sequential Notation Framework for Probabilistic Graph Generation — arXiv:2610.19781},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19781},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f649d316fd02; sha256 58cedbfee4519f735308c59012963d02267782611760deedb18244de81b56044},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19781. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce SNACK, a string representation for probabilistic graph generation that enables sequence models to generate and model graphs with discrete node and edge features. SNACK linearizes graphs by encoding the nonzero entries of the lower-triangular adjacency matrix, establishing a bijective correspondence between valid sequences and ordered adjacency matrices. This design enables invalid logit masking to enforce structural constraints--such as chemical valence and ordering rules--guaranteeing 100% valid generated sequences. SNACK also enables principled string-based GFlowNet training by explicitly accounting for node-ordering symmetries. Across standard graph-generation tasks and molecular distribution-learning benchmarks, SNACK achieves competitive sample quality, while substantially improving the throughput of GFlowNet training relative to graph-based generation. Probing analyses further show that models trained on SNACK encode meaningful local and global graph structure despite receiving only sequential supervision. These results position SNACK as a practical framework for probabilistic graph generation with deep sequence models. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.19781 — 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 2026-10-15T13:53:35.904Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).