论文标题
梯子：具有生成先验的潜在数据分发建模
LaDDer: Latent Data Distribution Modelling with a Generative Prior
论文作者
论文摘要
在本文中，我们表明，学到的生成模型的性能与该模型准确表示所推论的\ textbf {潜在数据分布}的能力密切相关，即其拓扑和结构属性。我们建议梯子在变分自动编码器框架中实现潜在数据分布的准确建模，并促进更好的表示。梯子的核心思想是一个元装置概念，它使用多个VAE模型来学习嵌入的嵌入，形成了编码的阶梯。我们使用非参数混合物作为最内向的超级先验，并在统一的变化框架中学习所有参数。从广泛的实验中，我们表明我们的梯子模型能够准确估计复杂的潜在分布并改善表示质量。我们还提出了一种利用派生数据分布的新型潜在空间插值方法。
In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We propose LaDDer to achieve accurate modelling of the latent data distribution in a variational autoencoder framework and to facilitate better representation learning. The central idea of LaDDer is a meta-embedding concept, which uses multiple VAE models to learn an embedding of the embeddings, forming a ladder of encodings. We use a non-parametric mixture as the hyper prior for the innermost VAE and learn all the parameters in a unified variational framework. From extensive experiments, we show that our LaDDer model is able to accurately estimate complex latent distribution and results in improvement in the representation quality. We also propose a novel latent space interpolation method that utilises the derived data distribution.
