REVIEW 4 cited by
Diffusion Models for Graphs Benefit From Discrete State Spaces
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 4 Pith papers
-
A collaborative constrained graph diffusion model for the generation of realistic synthetic molecules
A valence-preserving double edge-swap diffusion model with a learned time estimator generates chemically valid molecules with property distributions closer to real molecules than JTVAE and DiGress on the GuacaMol benchmark.
-
Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models
Removing explicit noise-level conditioning from graph diffusion models is often harmless, and the paper gives concentration and error-propagation bounds explaining why, with supporting experiments on QM9 and soc-Epinions1.
-
Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities
Satellite imagery plus population is enough to generate commuting origin-destination flows that closely match models using detailed sociodemographic and point-of-interest data.
-
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Discrete diffusion models are re-framed as instances of a tokenization-centric, four-component design space (corruption, denoiser, objective, sampler) in a broad survey with no new experimental or theoretical results.
Discussion (0). Continue with ORCID to comment.