arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.07046cs.LGstat.ML
收藏

基于流形优化的解纠缠表示学习与生成

Disentangled Representation Learning and Generation with Manifold Optimization

KU Leuven(鲁汶大学);Université de Lille(里尔大学);CNRS(法国国家科学研究中心);Centrale Lille(里尔中央理工学院)

Arun Pandey, Michael Fanuel, Joachim Schreurs, Johan A. K. Suykens

摘要:

解纠缠是表示学习中的一个有用属性,它增加了生成模型的可解释性,例如变分自编码器(VAE),生成对抗模型及其许多变体。通常在这样的模型中,解缠结性能的增加与生成质量相权衡。在潜在空间模型的背景下,这项工作提出了一个表示学习框架,该框架通过鼓励变化的正交方向来显式促进解开纠缠。建议的目标是一个自动编码器的误差项的总和,以及在特征空间中的主成分分析重建误差。这有一个解释的限制核机器的特征向量矩阵价值的Stiefel流形。我们的分析表明,这样的结构促进解纠缠匹配的主要方向在潜在的空间与数据空间中的正交变化的方向。在交替最小化方案中,我们使用Cayley ADAM算法-Stiefel流形上的随机优化方法以及ADAM优化器。我们的理论讨论和各种实验表明,该模型提高了许多VAE变种的生成质量和解开表示学习。

英文摘要:

Disentanglement is a useful property in representation learning which increases the interpretability of generative models such as Variational autoencoders (VAE), Generative Adversarial Models, and their many variants. Typically in such models, an increase in disentanglement performance is traded-off with generation quality. In the context of latent space models, this work presents a representation learning framework that explicitly promotes disentanglement by encouraging orthogonal directions of variations. The proposed objective is the sum of an autoencoder error term along with a Principal Component Analysis reconstruction error in the feature space. This has an interpretation of a Restricted Kernel Machine with the eigenvector matrix-valued on the Stiefel manifold. Our analysis shows that such a construction promotes disentanglement by matching the principal directions in the latent space with the directions of orthogonal variation in data space. In an alternating minimization scheme, we use Cayley ADAM algorithm - a stochastic optimization method on the Stiefel manifold along with the ADAM optimizer. Our theoretical discussion and various experiments show that the proposed model improves over many VAE variants in terms of both generation quality and disentangled representation 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。

↑