This work introduces DiGress, a discrete denoising diffusion model for
generating graphs with categorical node and edge attributes. Our model utilizes
a discrete diffusion process that progressively edits graphs with noise,
through the process of adding or removing edges and changing the categories. A
graph transformer network is trained to revert this process, simplifying the
problem of distribution learning over graphs into a sequence of node and edge
classification tasks. We further improve sample quality by introducing a
Markovian noise model that preserves the marginal distribution of node and edge
types during diffusion, and by incorporating auxiliary graph-theoretic
features. A procedure for conditioning the generation on graph-level features
is also proposed. DiGress achieves state-of-the-art performance on molecular
and non-molecular datasets, with up to 3x validity improvement on a planar
graph dataset. It is also the first model to scale to the large GuacaMol
dataset containing 1.3M drug-like molecules without the use of
molecule-specific representations.

本文介绍了 DiGress，一种用于生成具有分类节点和边缘属性的图形的离散去噪扩散模型。通过逐步添加或删除边缘和更改类别的过程，我们的模型利用离散扩散过程逐步编辑具有噪声的图形。同时，我们还提出了一种控制生成过程的图级特征的程序，并使用了马尔可夫噪声模型和辅助图理论特征，进一步提高了样本质量。DiGress 在分子和非分子数据集上取得了最先进的性能，在平面图数据集上有效性提高了 3 倍。此外，该模型是首个能够不使用分子特定表示就能扩展到包含 130 万药物分子的大型 GuacaMol 数据集的模型。