arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.06223cs.LG
收藏

用于学习函数上分布的超生成器变分混合模型

Variational Mixture of HyperGenerators for Learning Distributions Over Functions

Saarland University(萨尔兰大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Universidad Carlos III de Madrid(马德里卡洛斯三世大学)

Batuhan Koyuncu, Pablo Sanchez-Martin, Ignacio Peis, Pablo M. Olmos, Isabel Valera

AI总结:

针对现有基于隐式神经表示的函数空间生成模型推理任务成本高、能力弱的问题,提出结合INRs、VAE、归一化流与混合超网络的VAMoH模型,可高效学习函数分布并在多类推理任务上表现更优。

摘要:

近期的方法基于隐式神经表示(INRs)提出了函数空间上的生成模型,但这类方法在处理缺失数据插补等推理任务时计算成本高昂,甚至完全无法应对此类任务。本研究提出了一种新型深度生成模型,命名为VAMoH。VAMoH结合了利用INRs建模连续函数的能力,以及变分自编码器(VAEs)的推理能力。此外,VAMoH依托归一化流定义先验分布,并采用混合超网络对数据对数似然进行参数化,这赋予了VAMoH强大的表达能力与可解释性。通过在图像、体素、气候数据等多种数据类型上开展实验,我们证明VAMoH能够有效学习连续函数上的丰富分布。此外,它在条件超分辨率生成、图像修复等推理相关任务上的表现与现有方法相当甚至更优,同时计算需求更低。

英文摘要:

Recent approaches build on implicit neural representations (INRs) to propose generative models over function spaces. However, they are computationally costly when dealing with inference tasks, such as missing data imputation, or directly cannot tackle them. In this work, we propose a novel deep generative model, named VAMoH. VAMoH combines the capabilities of modeling continuous functions using INRs and the inference capabilities of Variational Autoencoders (VAEs). In addition, VAMoH relies on a normalizing flow to define the prior, and a mixture of hypernetworks to parametrize the data log-likelihood. This gives VAMoH a high expressive capability and interpretability. Through experiments on a diverse range of data types, such as images, voxels, and climate data, we show that VAMoH can effectively learn rich distributions over continuous functions. Furthermore, it can perform inference-related tasks, such as conditional super-resolution generation and in-painting, as well or better than previous approaches, while being less computationally demanding.

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。

↑