用贝叶斯推断生成图结构，一次完成且性能领先
Discrete Bayesian Sample Inference for Graph Generation
- 基于贝叶斯样本推断，在分布参数空间迭代优化图信念
- 在Moses和GuacaMol上超越现有单次生成模型
- 适合分子生成与知识图谱等离散结构建模任务
生成图结构数据在分子生成、知识图谱和网络分析中至关重要。然而，其离散、无序特性使传统生成模型难以处理，催生了离散扩散与流匹配模型。本文提出GraphBSI，一种基于贝叶斯样本推断（BSI）的单次图生成模型。不同于直接演化样本，GraphBSI在分布参数的连续空间中迭代精炼图的信念，自然处理离散结构。进一步，我们将BSI表述为随机微分方程（SDE），推导出一种噪声控制的SDE族，通过分数函数近似保持边缘分布。理论分析揭示其与贝叶斯流网络及扩散模型的联系。实验表明，GraphBSI在分子和合成图生成基准上达到顶尖性能，优于Moses和GuacaMol上的现有单次生成模型。
原文摘要 · Abstract (English)
Generating graph-structured data is crucial in applications such as molecular generation, knowledge graphs, and network analysis. However, their discrete, unordered nature makes them difficult for traditional generative models, leading to the rise of discrete diffusion and flow matching models. In this work, we introduce GraphBSI, a novel one-shot graph generative model based on Bayesian Sample Inference (BSI). Instead of evolving samples directly, GraphBSI iteratively refines a belief over graphs in the continuous space of distribution parameters, naturally handling discrete structures. Further, we state BSI as a stochastic differential equation (SDE) and derive a noise-controlled family of SDEs that preserves the marginal distributions via an approximation of the score function. Our theoretical analysis further reveals the connection to Bayesian Flow Networks and Diffusion models. Finally, in our empirical evaluation, we demonstrate state-of-the-art performance on molecular and synthetic graph generation, outperforming existing one-shot graph generative models on the standard benchmarks Moses and GuacaMol.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。