Diffusion Models for Graphs Benefit From Discrete State Spaces
Abstract
Denoising diffusion probabilistic models and score-matching models have proven to be very powerful for generative tasks. While these approaches have also been applied to the generation of discrete graphs, they have, so far, relied on continuous Gaussian perturbations. Instead, in this work, we suggest using discrete noise for the forward Markov process. This ensures that in every intermediate step the graph remains discrete. Compared to the previous approach, our experimental results on four datasets and multiple architectures show that using a discrete noising process results in higher quality generated samples indicated with an average MMDs reduced by a factor of 1.5. Furthermore, the number of denoising steps is reduced from 1000 to 32 steps, leading to a 30 times faster sampling procedure.
Keywords
Cite
@article{arxiv.2210.01549,
title = {Diffusion Models for Graphs Benefit From Discrete State Spaces},
author = {Kilian Konstantin Haefeli and Karolis Martinkus and Nathanaël Perraudin and Roger Wattenhofer},
journal= {arXiv preprint arXiv:2210.01549},
year = {2023}
}
Comments
Presented at the First Learning on Graphs Conference (LoG 2022) and the NeurIPS 2022 New Frontiers in Graph Learning Workshop (NeurIPS GLFrontiers 2022)