生成3D生物图谱时保持结构与语义一致性，提升下游任务性能。
Semantically Consistent Discrete Diffusion for 3D Biological Graph Modeling
- 采样时用新投影算子随机修复不一致，确保生成图合理
- 采用边删除式噪声过程，适配稀疏生物图谱结构
- 生成样本可直接用于链接预测，且提升标注任务效果
3D空间图在生物和临床研究中至关重要，用于建模血管、神经元和气道等解剖网络。然而，现有基于扩散的方法在生成过程中难以保证解剖合理性。本文提出一种新型3D生物图生成方法，满足结构与语义合理性。通过在采样阶段引入新颖的投影算子，随机修正不一致；并采用基于边删除的噪声过程，更适合稀疏生物图。在人类 Willis 圈和肺气道两个真实数据集上，该方法表现优于以往方法。更重要的是，生成样本显著提升了下游图标注任务性能，且无需微调即可作为开箱即用的链接预测器使用。
原文摘要 · Abstract (English)
3D spatial graphs play a crucial role in biological and clinical research by modeling anatomical networks such as blood vessels,neurons, and airways. However, generating 3D biological graphs while maintaining anatomical validity remains challenging, a key limitation of existing diffusion-based methods. In this work, we propose a novel 3D biological graph generation method that adheres to structural and semantic plausibility conditions. We achieve this by using a novel projection operator during sampling that stochastically fixes inconsistencies. Further, we adopt a superior edge-deletion-based noising procedure suitable for sparse biological graphs. Our method demonstrates superior performance on two real-world datasets, human circle of Willis and lung airways, compared to previous approaches. Importantly, we demonstrate that the generated samples significantly enhance downstream graph labeling performance. Furthermore, we show that our generative model is a reasonable out-of-the-box link predictior.
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。