DiGress: Discrete Denoising diffusion for graph generation
arXiv:2209.14734
Abstract
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.
22 pages. Published as a conference paper at ICLR 2023
Cited by in corpus (6)
- A generative artificial intelligence framework based on a molecular diffusion model for the design of metal-organic frameworks for carbon capture
- A Diffusion model for POI recommendation
- DALLE-URBAN: Capturing the urban design expertise of large text to image transformers
- Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
- Unraveling the Potential of Diffusion Models in Small Molecule Generation
- A Bayesian Flow Network Framework for Chemistry Tasks