Information Constraints on Auto-Encoding Variational Bayes
Information Constraints on Auto-Encoding Variational Bayes
复制标题
DOI：
--
复制
发表时间：
2018-05
期刊：
影响因子：
--
通讯作者：
Romain Lopez;J. Regier;N. Yosef;Michael I. Jordan
中科院分区：
文献类型：
--
作者：
Romain Lopez;J. Regier;N. Yosef;Michael I. Jordan
使用神经网络参数化生成模型的近似后验已成为最近机器学习研究的一个共同主题。这种方法虽然具有吸引人的灵活性，但却难以施加或评估有条件独立等结构性限制。我们提出了一个框架，学习表示依赖于自动编码变分贝叶斯和搜索空间的约束，通过基于内核的独立性措施。特别是，我们的方法采用了$d$-变量希尔伯特-施密特独立性准则（dHSIC），以强制执行的潜在表示和任意滋扰因素之间的独立性。我们展示了如何将这种方法应用于一系列问题，包括学习不变表示和学习可解释表示的问题。我们还提出了一个完整的应用程序，单细胞RNA测序（scRNA-seq）。在这种情况下，生物信号以复杂的方式与测序误差和采样效应混合。我们表明，我们的方法在这一领域的最先进的表现。
Parameterizing the approximate posterior of a generative model with neural networks has become a common theme in recent machine learning research. While providing appealing flexibility, this approach makes it difficult to impose or assess structural constraints such as conditional independence. We propose a framework for learning representations that relies on Auto-Encoding Variational Bayes and whose search space is constrained via kernel-based measures of independence. In particular, our method employs the $d$-variable Hilbert-Schmidt Independence Criterion (dHSIC) to enforce independence between the latent representations and arbitrary nuisance factors. We show how to apply this method to a range of problems, including the problems of learning invariant representations and the learning of interpretable representations. We also present a full-fledged application to single-cell RNA sequencing (scRNA-seq). In this setting the biological signal is mixed in complex ways with sequencing errors and sampling effects. We show that our method out-performs the state-of-the-art in this domain.