arXiv：cs.LG· Hohyun Kim, Hyesung Kim, Min-hwan Oh, Seunggeun Lee·· 10 小时前
SNACK：面向概率图生成的序列化表示框架
SNACK: A Sequential Notation Framework for Probabilistic Graph Generation
AI 导读
SNACK 是一种将图线性化为字符串的概率图生成表示方法，通过编码下三角邻接矩阵的非零项，建立合法序列与有序邻接矩阵的双射，并用非法 logit 掩码保证 100% 合法生成序列。
正文
Abstract: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.
| Comments: | 30 pages; Accepted at NeurIPS 2026 |
| Subjects: | Machine Learning (stat.ML); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.19781 [stat.ML] |
| (or arXiv:2610.19781v1 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19781 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hohyun Kim [view email]
[v1]
Wed, 14 Oct 2026 08:30:23 UTC (634 KB)
来源：arXiv：cs.LG · arxiv.org