arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.09064cond-mat.stat-mechcond-mat.dis-nncs.LGphysics.app-phphysics.bio-ph
收藏

带逆重整化群流的生成式扩散模型

Generative diffusion model with inverse renormalization group flows

The University of Tokyo(东京大学);Institute for Physics of Intelligence, The University of Tokyo(东京大学智能物理研究所)

Kanta Masuki, Yuto Ashida

AI总结:

针对传统扩散模型忽略数据多尺度结构、生成速度慢的问题,提出基于重整化群流的扩散模型,通过逆重整化群流从粗到细生成样本,在蛋白质结构预测和图像生成任务上性能更优、速度更快。

摘要:

扩散模型是一类通过对被白噪声污染的样本进行去噪来生成数据的生成模型。尽管扩散模型在计算机视觉、音频合成和点云生成领域取得了成功,但目前它们忽略了数据中固有的多尺度结构,并且由于迭代步骤多,生成过程缓慢。在物理学中,重整化群(renormalization group)为连接不同尺度并给出准确的粗粒度模型提供了一个基础框架。本文提出一种基于重整化群的扩散模型,该模型利用数据分布的多尺度特性实现高质量的数据生成。遵循重整化群流程的思路,我们定义了一个流方程,该方程从精细尺度细节到粗粒度结构逐步擦除数据信息。通过逆转重整化群流,我们的模型能够以从粗到细的方式生成高质量样本。我们通过将该模型应用于蛋白质结构预测和图像生成,验证了其通用性。在标准评估指标上,我们的模型始终优于传统扩散模型,提升了样本质量,并且/或者将采样速度加快了一个数量级。所提出的方法减少了生成式扩散模型中依赖数据的超参数调优需求,展现出基于重整化群概念系统性提升采样效率的前景。

英文摘要:

Diffusion models represent a class of generative models that produce data by denoising a sample corrupted by white noise. Despite the success of diffusion models in computer vision, audio synthesis, and point cloud generation, so far they overlook inherent multiscale structures in data and have a slow generation process due to many iteration steps. In physics, the renormalization group offers a fundamental framework for linking different scales and giving an accurate coarse-grained model. Here we introduce a renormalization group-based diffusion model that leverages multiscale nature of data distributions for realizing a high-quality data generation. In the spirit of renormalization group procedures, we define a flow equation that progressively erases data information from fine-scale details to coarse-grained structures. Through reversing the renormalization group flows, our model is able to generate high-quality samples in a coarse-to-fine manner. We validate the versatility of the model through applications to protein structure prediction and image generation. Our model consistently outperforms conventional diffusion models across standard evaluation metrics, enhancing sample quality and/or accelerating sampling speed by an order of magnitude. The proposed method alleviates the need for data-dependent tuning of hyperparameters in the generative diffusion models, showing promise for systematically increasing sample efficiency based on the concept of the renormalization group.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑