发表机构
School of Electrical Engineering and Computer Science, The University of Queensland; Institute for Molecular Bioscience, The University of Queensland; Chinese Academy of Sciences; Department of Computer Science, City University of Hong Kong（昆士兰大学电气工程与计算机科学学院; 昆士兰大学分子生物科学研究所; 中国科学院; 香港城市大学计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出嵌入式图流（EGF）生成模型，学习节点与边类别连续嵌入，在 QM9、ZINC250k 分子基准测试中性能优于基线方法，生成分类图表现优异。
AI 中文摘要
生成分类图需要选择节点和边类型，以形成连贯结构且不依赖节点顺序。许多图生成器将类别编码为固定的独热向量，这可能会引入人为几何结构，使类别等距。我们提出嵌入式图流（Embedded Graph Flows，EGF），这是一种生成模型，它学习节点和无序边类别的连续嵌入，并使用排列等变图变换器将高斯噪声传输到这些学习到的端点。最终读出器将嵌入映射回离散图类别。在分子基准测试中，EGF 取得了具有竞争力的性能。在 QM9 上，EGF 在报告的所有四个指标中均优于三种方法，其中 Fréchet ChemNet 距离（FCD）为 0.150，而基于分类扩散的基线 DiGress 为 0.717，基于桥接的基线 GruM 为 0.812。当应用于 ZINC250k 中更大的分子时，EGF 使用邻域子图成对距离核（NSPDK）保持最低的最大均值差异（MMD），表明与参考分子的局部子结构高度一致。我们的代码可在此 https URL 获取。
英文摘要
Generating categorical graphs requires choosing node and edge types that form a coherent structure without depending on node order. Many graph generators encode categories as fixed one-hot vectors, which can impose an artificial geometry in which categories are equidistant. We propose Embedded Graph Flows (EGF), a generative model that learns continuous embeddings for node and unordered-edge categories and transports Gaussian noise towards these learnt endpoints using a permutation-equivariant graph transformer. A terminal readout maps the embeddings back to discrete graph categories. Across molecular benchmarks, EGF achieved competitive performance. On QM9, EGF gives the best result on all four reported metrics among the three methods, including a Fréchet ChemNet Distance (FCD) of 0.150, compared with 0.717 for the categorical-diffusion baseline DiGress and 0.812 for the bridge-based baseline GruM. When applied to larger molecules in ZINC250k, EGF retains the lowest maximum mean discrepancy (MMD) using the neighbourhood subgraph pairwise distance kernel (NSPDK), indicating close agreement with the local substructures of the reference molecules. Our code is available at https://github.com/Trusted-System-Lab/EGF.
