Bibliographic Details
| Title: |
DiGress: Discrete Denoising diffusion for graph generation |
| Authors: |
Vignac, Clement, Krawczuk, Igor, Siraudin, Antoine, Wang, Bohan, Cevher, Volkan, Frossard, Pascal |
| Source: |
International Conference on Learning Representations (ICLR 2023) |
| Publication Year: |
2022 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Machine Learning |
| More Details: |
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.
Comment: 22 pages. Published as a conference paper at ICLR 2023 |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2209.14734 |
| Accession Number: |
edsarx.2209.14734 |
| Database: |
arXiv |
