arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.05461cs.LGstat.ML
收藏

在不可比空间中学习生成模型

Learning Generative Models across Incomparable Spaces

Eidgenössische Technische Hochschule (ETH)(苏黎世联邦理工学院);Massachusetts Institute of Technology (MIT)(麻省理工学院)

Charlotte Bunne, David Alvarez-Melis, Andreas Krause, Stefanie Jegelka

摘要:

生成对抗网络在学习一个完整的参考分布方面取得了显著的成功。然而,在某些情况下,我们可能只想学习某些方面(例如,簇或歧管结构),同时修改其它结构(例如,样式、方向或尺寸)。在这项工作中,我们提出了一种在这种无与伦比的空间中学习生成模型的方法,并演示了如何将学习的分布转向目标属性。我们模型的一个关键组成部分是Gromov-Wasserstein距离,这是一个差异的概念,它比较了相关而不是绝对的分布。虽然该框架将当前的生成模型包含在相同的再生分布中,但其固有的灵活性允许应用于流形学习,关系学习和跨域学习中的任务。

英文摘要:

Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety. However, in some cases, we may want to only learn some aspects (e.g., cluster or manifold structure), while modifying others (e.g., style, orientation or dimension). In this work, we propose an approach to learn generative models across such incomparable spaces, and demonstrate how to steer the learned distribution towards target properties. A key component of our model is the Gromov-Wasserstein distance, a notion of discrepancy that compares distributions relationally rather than absolutely. While this framework subsumes current generative models in identically reproducing distributions, its inherent flexibility allows application to tasks in manifold learning, relational learning and cross-domain learning.

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。

↑