arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.10349cs.LGcs.AIcs.CVstat.ML
收藏

对抗典型相关分析

Adversarial Canonical Correlation Analysis

North Carolina State University(北卡罗来纳州立大学)

Benjamin Dutton

摘要:

典型相关分析(CCA)是一种统计技术,用于从多个数据源或视图中提取公共信息。它已被用于各种表示学习问题,如降维,词嵌入和聚类。最近的工作在深度学习上下文中给出了CCA概率基础,并使用数据日志似然的变分下界来估计模型参数。另外,对抗技术近年来已经出现,作为自动编码器中变分贝叶斯方法的强大替代方案。在这项工作中,我们探索了最近在深度变分CCA(VCCA和VCCA-Private)中工作的直接对抗性替代方案,我们称之为ACCA和ACCA-Private,并展示了这些方法如何提供更强大,更灵活的方式来匹配来自编码器的近似后验,比VCCA和VCCA-Private模型更大的先验类别。这允许更直接地追求构成良好表示的新先验,例如解开变化的潜在因素。我们通过使用一个新设计的数据集,我们称之为缠结MNIST,提供进一步的分析VCCA-Private和ACCA-Private的多层次解纠缠特性。我们还为这些模型设计了一个验证标准,该标准在理论上是有基础的,与任务无关的,并且在实践中效果良好。最后,我们填补了一个小的研究空白,推导出一个额外的可变下限VCCA,允许表示使用特定于视图的信息,从两个输入视图。

英文摘要:

Canonical Correlation Analysis (CCA) is a statistical technique used to extract common information from multiple data sources or views. It has been used in various representation learning problems, such as dimensionality reduction, word embedding, and clustering. Recent work has given CCA probabilistic footing in a deep learning context and uses a variational lower bound for the data log likelihood to estimate model parameters. Alternatively, adversarial techniques have arisen in recent years as a powerful alternative to variational Bayesian methods in autoencoders. In this work, we explore straightforward adversarial alternatives to recent work in Deep Variational CCA (VCCA and VCCA-Private) we call ACCA and ACCA-Private and show how these approaches offer a stronger and more flexible way to match the approximate posteriors coming from encoders to much larger classes of priors than the VCCA and VCCA-Private models. This allows new priors for what constitutes a good representation, such as disentangling underlying factors of variation, to be more directly pursued. We offer further analysis on the multi-level disentangling properties of VCCA-Private and ACCA-Private through the use of a newly designed dataset we call Tangled MNIST. We also design a validation criteria for these models that is theoretically grounded, task-agnostic, and works well in practice. Lastly, we fill a minor research gap by deriving an additional variational lower bound for VCCA that allows the representation to use view-specific information from both input views.

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。

↑