Cometh: A continuous-time discrete-state graph diffusion model
- URL: http://arxiv.org/abs/2406.06449v1
- Date: Mon, 10 Jun 2024 16:39:39 GMT
- Title: Cometh: A continuous-time discrete-state graph diffusion model
- Authors: Antoine Siraudin, Fragkiskos D. Malliaros, Christopher Morris,
- Abstract summary: We propose Cometh, a continuous-time discrete-state graph diffusion model, integrating graph data into a continuous-time diffusion model framework.
We show that integrating continuous time leads to significant improvements across various metrics over state-of-the-art discrete-state diffusion models.
- Score: 8.444907767842228
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Discrete-state denoising diffusion models led to state-of-the-art performance in graph generation, especially in the molecular domain. Recently, they have been transposed to continuous time, allowing more flexibility in the reverse process and a better trade-off between sampling efficiency and quality. Here, to leverage the benefits of both approaches, we propose Cometh, a continuous-time discrete-state graph diffusion model, integrating graph data into a continuous-time diffusion model framework. Empirically, we show that integrating continuous time leads to significant improvements across various metrics over state-of-the-art discrete-state diffusion models on a large set of molecular and non-molecular benchmark datasets.
Related papers
- SigDiffusions: Score-Based Diffusion Models for Long Time Series via Log-Signature Embeddings [3.801509221714223]
We introduce SigDiffusion, a novel diffusion model operating on log-signatures of the data.
To recover a signal from its log-signature formulae, we provide new closed-form inversion formulae.
We show that combining SigDiffusion with these formulae results in highly realistic time series generation.
arXiv Detail & Related papers (2024-06-14T18:04:06Z) - Discrete-state Continuous-time Diffusion for Graph Generation [46.626952802292074]
Diffusion generative models have been applied to graph generation tasks.
We formulate the graph diffusion generation in a discrete-state continuous-time setting.
Our proposed model shows competitive empirical performance against state-of-the-art graph generation solutions.
arXiv Detail & Related papers (2024-05-19T00:09:42Z) - Convergence Analysis of Discrete Diffusion Model: Exact Implementation
through Uniformization [17.535229185525353]
We introduce an algorithm leveraging the uniformization of continuous Markov chains, implementing transitions on random time points.
Our results align with state-of-the-art achievements for diffusion models in $mathbbRd$ and further underscore the advantages of discrete diffusion models in comparison to the $mathbbRd$ setting.
arXiv Detail & Related papers (2024-02-12T22:26:52Z) - Time Series Diffusion in the Frequency Domain [54.60573052311487]
We analyze whether representing time series in the frequency domain is a useful inductive bias for score-based diffusion models.
We show that a dual diffusion process occurs in the frequency domain with an important nuance.
We show how to adapt the denoising score matching approach to implement diffusion models in the frequency domain.
arXiv Detail & Related papers (2024-02-08T18:59:05Z) - Fast Sampling via Discrete Non-Markov Diffusion Models [49.598085130313514]
We propose a discrete non-Markov diffusion model, which admits an accelerated reverse sampling for discrete data generation.
Our method significantly reduces the number of function evaluations (i.e., calls to the neural network), making the sampling process much faster.
arXiv Detail & Related papers (2023-12-14T18:14:11Z) - Score-based Continuous-time Discrete Diffusion Models [102.65769839899315]
We extend diffusion models to discrete variables by introducing a Markov jump process where the reverse process denoises via a continuous-time Markov chain.
We show that an unbiased estimator can be obtained via simple matching the conditional marginal distributions.
We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
arXiv Detail & Related papers (2022-11-30T05:33:29Z) - Diffusion Models in Vision: A Survey [80.82832715884597]
A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage.
Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens.
arXiv Detail & Related papers (2022-09-10T22:00:30Z) - How Much is Enough? A Study on Diffusion Times in Score-based Generative
Models [76.76860707897413]
Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution.
We show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process.
arXiv Detail & Related papers (2022-06-10T15:09:46Z) - A Continuous Time Framework for Discrete Denoising Models [43.135447812798155]
We provide the first complete continuous time framework for denoising diffusion models of discrete data.
This is achieved by formulating the forward noising process and corresponding reverse time generative process as Continuous Time Markov Chains (CTMCs)
arXiv Detail & Related papers (2022-05-30T10:37:41Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.