Variational autoencoders (VAEs), as well as other generative models, have been shown to be efficient and accurate for capturing the latent structure of vast amounts of complex high-dimensional data. However, existing VAEs can still not directly handle data that are heterogenous (mixed continuous and discrete) or incomplete (with missing data at random), which is indeed common in real-world applications. In this paper, we propose a general framework to design VAEs suitable for fitting incomplete heterogenous data. The proposed HI-VAE includes likelihood models for real-valued, positive real valued, interval, categorical, ordinal and count data, and allows accurate estimation (and potentially imputation) of missing data. Furthermore, HI-VAE presents competitive predictive performance in supervised tasks, outperforming supervised models when trained on incomplete data.

中文翻译：

---

使用 VAE 处理不完整的异构数据

变分自编码器 (VAE) 以及其他生成模型已被证明可以有效且准确地捕获大量复杂高维数据的潜在结构。然而，现有的 VAE 仍然无法直接处理异构（混合连续和离散）或不完整（随机丢失数据）的数据，这在实际应用中确实很常见。在本文中，我们提出了一个通用框架来设计适用于拟合不完整异构数据的 VAE。提议的 HI-VAE 包括实值、正实值、区间、分类、序数和计数数据的似然模型，并允许对缺失数据进行准确估计（和潜在的估算）。此外，HI-VAE 在监督任务中表现出有竞争力的预测性能，