arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.02747cs.LGcs.AIstat.ML
收藏

生成式建模的流匹配

Flow Matching for Generative Modeling

Meta AI (FAIR)(元人工智能(基础人工智能研究团队));Weizmann Institute of Science(魏茨曼科学研究所)

Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, Maximilian Nickel, Matt Le

摘要:

我们引入了一个新的范例生成建模建立在连续规范化流(CNFs),使我们能够训练CNFs在前所未有的规模。具体来说,我们提出了流匹配(FM)的概念,模拟免费的方法训练CNFs的基础上回归向量场的固定条件概率路径。流匹配与用于在噪声和数据样本之间进行转换的高斯概率路径的一般族兼容--其将现有的扩散路径作为特定实例。有趣的是,我们发现,采用FM与扩散路径的结果在一个更强大和稳定的替代训练扩散模型。此外,流匹配为用其他非扩散概率路径训练CNF打开了大门。一个特别有趣的例子是使用最优运输(OT)位移插值来定义条件概率路径。这些路径比扩散路径更有效,提供更快的训练和采样,并导致更好的泛化。在ImageNet上使用流匹配训练CNF在可能性和样本质量方面都比其他基于扩散的方法具有更好的性能,并且可以使用现成的数值ODE求解器快速可靠地生成样本。

英文摘要:

We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for training CNFs based on regressing vector fields of fixed conditional probability paths. Flow Matching is compatible with a general family of Gaussian probability paths for transforming between noise and data samples -- which subsumes existing diffusion paths as specific instances. Interestingly, we find that employing FM with diffusion paths results in a more robust and stable alternative for training diffusion models. Furthermore, Flow Matching opens the door to training CNFs with other, non-diffusion probability paths. An instance of particular interest is using Optimal Transport (OT) displacement interpolation to define the conditional probability paths. These paths are more efficient than diffusion paths, provide faster training and sampling, and result in better generalization. Training CNFs using Flow Matching on ImageNet leads to consistently better performance than alternative diffusion-based methods in terms of both likelihood and sample quality, and allows fast and reliable sample generation using off-the-shelf numerical ODE solvers.

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。

↑