DiGress: Discrete Denoising diffusion for graph generation

Clement Vignac, Igor Krawczuk, Antoine Siraudin, Bohan Wang, Volkan Cevher, Pascal Frossard

Keywords: Graph generation, Denoising Diffusion Model, Molecule Generation, Permutation Equivariance, Discrete Diffusion

TL;DR: We propose a discrete denoising diffusion model for generating graphs with categorical node and edge attributes. It is state-of-the-art on both abstract and molecular datasets.

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.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Generative models

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2209.14734/code)