Unlocking Guidance for Discrete State-Space Diffusion and Flow Models
- URL: http://arxiv.org/abs/2406.01572v1
- Date: Mon, 3 Jun 2024 17:51:54 GMT
- Title: Unlocking Guidance for Discrete State-Space Diffusion and Flow Models
- Authors: Hunter Nisonoff, Junhao Xiong, Stephan Allenspach, Jennifer Listgarten,
- Abstract summary: We introduce a general and principled method for applying guidance on discrete state-space models.
We demonstrate the utility of our approach on a range of applications including guided generation of images, small-molecules, DNA sequences and protein sequences.
- Score: 1.7749342709605143
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Generative models on discrete state-spaces have a wide range of potential applications, particularly in the domain of natural sciences. In continuous state-spaces, controllable and flexible generation of samples with desired properties has been realized using guidance on diffusion and flow models. However, these guidance approaches are not readily amenable to discrete state-space models. Consequently, we introduce a general and principled method for applying guidance on such models. Our method depends on leveraging continuous-time Markov processes on discrete state-spaces, which unlocks computational tractability for sampling from a desired guided distribution. We demonstrate the utility of our approach, Discrete Guidance, on a range of applications including guided generation of images, small-molecules, DNA sequences and protein sequences.
Related papers
- Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian
Mixture Models [59.331993845831946]
Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties.
This paper provides the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models.
arXiv Detail & Related papers (2024-03-03T23:15:48Z) - Synthetic location trajectory generation using categorical diffusion
models [50.809683239937584]
Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data.
We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
arXiv Detail & Related papers (2024-02-19T15:57:39Z) - 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) - Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design [37.634098563033795]
We present a new flow-based model of discrete data that provides the missing link in enabling flow-based generative models.
Our key insight is that the discrete equivalent of continuous space flow matching can be realized using Continuous Time Markov Chains.
We apply this capability to the task of protein co-design, wherein we learn a model for jointly generating protein structure and sequence.
arXiv Detail & Related papers (2024-02-07T16:15:36Z) - 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) - Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes [57.396578974401734]
We introduce a principled framework for building a generative diffusion process on general manifold.
Instead of following the denoising approach of previous diffusion models, we construct a diffusion process using a mixture of bridge processes.
We develop a geometric understanding of the mixture process, deriving the drift as a weighted mean of tangent directions to the data points.
arXiv Detail & Related papers (2023-10-11T06:04:40Z) - Infinite-Dimensional Diffusion Models [4.342241136871849]
We formulate diffusion-based generative models in infinite dimensions and apply them to the generative modeling of functions.
We show that our formulations are well posed in the infinite-dimensional setting and provide dimension-independent distance bounds from the sample to the target measure.
We also develop guidelines for the design of infinite-dimensional diffusion models.
arXiv Detail & Related papers (2023-02-20T18:00:38Z) - Free-Form Variational Inference for Gaussian Process State-Space Models [21.644570034208506]
We propose a new method for inference in Bayesian GPSSMs.
Our method is based on freeform variational inference via inducing Hamiltonian Monte Carlo.
We show that our approach can learn transition dynamics and latent states more accurately than competing methods.
arXiv Detail & Related papers (2023-02-20T11:34:16Z) - Diffusion Generative Models in Infinite Dimensions [10.15736468214228]
We generalize diffusion generative models to operate directly in function space.
A significant benefit of our function space point of view is that it allows us to explicitly specify the space of functions we are working in.
Our approach allows us to perform both unconditional and conditional generation of function-valued data.
arXiv Detail & Related papers (2022-12-01T21:54:19Z) - A Survey on Generative Diffusion Model [75.93774014861978]
Diffusion models are an emerging class of deep generative models.
They have certain limitations, including a time-consuming iterative generation process and confinement to high-dimensional Euclidean space.
This survey presents a plethora of advanced techniques aimed at enhancing diffusion models.
arXiv Detail & Related papers (2022-09-06T16:56:21Z) - Closed-Form Factorization of Latent Semantics in GANs [65.42778970898534]
A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images.
In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner.
We propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights.
arXiv Detail & Related papers (2020-07-13T18:05:36Z)
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.