Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding
- URL: http://arxiv.org/abs/2408.08252v5
- Date: Fri, 25 Oct 2024 02:50:44 GMT
- Title: Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding
- Authors: Xiner Li, Yulai Zhao, Chenyu Wang, Gabriele Scalia, Gokcen Eraslan, Surag Nair, Tommaso Biancalani, Shuiwang Ji, Aviv Regev, Sergey Levine, Masatoshi Uehara,
- Abstract summary: Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences.
We aim to optimize downstream reward functions while preserving the naturalness of these design spaces.
Our algorithm integrates soft value functions, which looks ahead to how intermediate noisy states lead to high rewards in the future.
- Score: 84.3224556294803
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. However, rather than merely generating designs that are natural, we often aim to optimize downstream reward functions while preserving the naturalness of these design spaces. Existing methods for achieving this goal often require ``differentiable'' proxy models (\textit{e.g.}, classifier guidance or DPS) or involve computationally expensive fine-tuning of diffusion models (\textit{e.g.}, classifier-free guidance, RL-based fine-tuning). In our work, we propose a new method to address these challenges. Our algorithm is an iterative sampling method that integrates soft value functions, which looks ahead to how intermediate noisy states lead to high rewards in the future, into the standard inference procedure of pre-trained diffusion models. Notably, our approach avoids fine-tuning generative models and eliminates the need to construct differentiable models. This enables us to (1) directly utilize non-differentiable features/reward feedback, commonly used in many scientific domains, and (2) apply our method to recent discrete diffusion models in a principled way. Finally, we demonstrate the effectiveness of our algorithm across several domains, including image generation, molecule generation, and DNA/RNA sequence generation. The code is available at \href{https://github.com/masa-ue/SVDD}{https://github.com/masa-ue/SVDD}.
Related papers
- Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics [7.873510219469276]
We introduce two novel training methods for discrete diffusion samplers.
These methods yield memory-efficient training and achieve state-of-the-art results in unsupervised optimization.
We introduce adaptations of SN-NIS and Neural Chain Monte Carlo that enable for the first time the application of discrete diffusion models to this problem.
arXiv Detail & Related papers (2025-02-12T18:59:55Z) - Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review [59.856222854472605]
This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models.
practical applications in fields such as biology often require sample generation that maximizes specific metrics.
We discuss (1) fine-tuning methods combined with inference-time techniques, (2) inference-time algorithms based on search algorithms such as Monte Carlo tree search, and (3) connections between inference-time algorithms in language models and diffusion models.
arXiv Detail & Related papers (2025-01-16T17:37:35Z) - RDPM: Solve Diffusion Probabilistic Models via Recurrent Token Prediction [17.005198258689035]
Diffusion Probabilistic Models (DPMs) have emerged as the de facto approach for high-fidelity image synthesis.
We introduce a novel generative framework, the Recurrent Diffusion Probabilistic Model (RDPM), which enhances the diffusion process through a recurrent token prediction mechanism.
arXiv Detail & Related papers (2024-12-24T12:28:19Z) - Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design [56.957070405026194]
We propose an algorithm that enables direct backpropagation of rewards through entire trajectories generated by diffusion models.
DRAKES can generate sequences that are both natural-like and yield high rewards.
arXiv Detail & Related papers (2024-10-17T15:10:13Z) - MING: A Functional Approach to Learning Molecular Generative Models [46.189683355768736]
This paper introduces a novel paradigm for learning molecule generative models based on functional representations.
We propose Molecular Implicit Neural Generation (MING), a diffusion-based model that learns molecular distributions in the function space.
arXiv Detail & Related papers (2024-10-16T13:02:02Z) - Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review [63.31328039424469]
This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions.
We explain the application of various RL algorithms, including PPO, differentiable optimization, reward-weighted MLE, value-weighted sampling, and path consistency learning.
arXiv Detail & Related papers (2024-07-18T17:35:32Z) - Diffusion-Model-Assisted Supervised Learning of Generative Models for
Density Estimation [10.793646707711442]
We present a framework for training generative models for density estimation.
We use the score-based diffusion model to generate labeled data.
Once the labeled data are generated, we can train a simple fully connected neural network to learn the generative model in the supervised manner.
arXiv Detail & Related papers (2023-10-22T23:56:19Z) - Mirror Diffusion Models for Constrained and Watermarked Generation [41.27274841596343]
Mirror Diffusion Models (MDM) is a new class of diffusion models that generate data on convex constrained sets without losing tractability.
For safety and privacy purposes, we also explore constrained sets as a new mechanism to embed invisible but quantitative information in generated data.
Our work brings new algorithmic opportunities for learning tractable diffusion on complex domains.
arXiv Detail & Related papers (2023-10-02T14:26:31Z) - Fast Sampling of Diffusion Models via Operator Learning [74.37531458470086]
We use neural operators, an efficient method to solve the probability flow differential equations, to accelerate the sampling process of diffusion models.
Compared to other fast sampling methods that have a sequential nature, we are the first to propose a parallel decoding method.
We show our method achieves state-of-the-art FID of 3.78 for CIFAR-10 and 7.83 for ImageNet-64 in the one-model-evaluation setting.
arXiv Detail & Related papers (2022-11-24T07:30:27Z) - 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)
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.