论文标题
分解的高斯流程变量自动编码器
Factorized Gaussian Process Variational Autoencoders
论文作者
论文摘要
各种自动编码器通常会假设各向同性高斯先验和均值田的后代，因此在我们可能期望在潜在变量之间相似性或一致性的情况下不会利用结构。高斯工艺变化自动编码器通过使用潜在的高斯过程来减轻此问题，但会导致立方推理时间复杂性。我们通过利用辅助特征的独立性来提出更可扩展的这些模型的扩展，该功能存在于许多数据集中。我们的模型将这些特征的潜在内核在不同的维度上分配，从而导致了显着的加速（在理论和实践中），同时与现有的不可估计方法相当地执行。此外，我们的方法允许对全球潜在信息进行其他建模，并提供更一般的外推，以看不见的输入组合。
Variational autoencoders often assume isotropic Gaussian priors and mean-field posteriors, hence do not exploit structure in scenarios where we may expect similarity or consistency across latent variables. Gaussian process variational autoencoders alleviate this problem through the use of a latent Gaussian process, but lead to a cubic inference time complexity. We propose a more scalable extension of these models by leveraging the independence of the auxiliary features, which is present in many datasets. Our model factorizes the latent kernel across these features in different dimensions, leading to a significant speed-up (in theory and practice), while empirically performing comparably to existing non-scalable approaches. Moreover, our approach allows for additional modeling of global latent information and for more general extrapolation to unseen input combinations.
