Irregularly sampled time series commonly occur in several domains where they present a significant challenge to standard deep learning models. In this paper, we propose a new deep learning framework for probabilistic interpolation of irregularly sampled time series that we call the Heteroscedastic Temporal Variational Autoencoder (HeTVAE). HeTVAE includes a novel input layer to encode information about input observation sparsity, a temporal VAE architecture to propagate uncertainty due to input sparsity, and a heteroscedastic output layer to enable variable uncertainty in output interpolations. Our results show that the proposed architecture is better able to reflect variable uncertainty through time due to sparse and irregular sampling than a range of baseline and traditional models, as well as recently proposed deep latent variable models that use homoscedastic output layers.
翻译:常规抽样时间序列通常发生在几个领域,这些领域对标准的深层学习模式提出了重大挑战。 在本文中,我们提出了一个新的深层次学习框架,用于对非常规抽样时间序列进行概率性内插,我们称之为HeTVAE(HeTVAE ) 。 HeTVAE 包括一个新的输入层,用于编码关于输入观察宽度的信息,一个用于传播输入宽度所致不确定性的时空VAE结构,以及一个能促成产出内插变量变异的超浮度输出层。我们的结果显示,拟议的结构比一系列基线和传统模型,以及最近提出的使用同源输出层的深潜伏变量模型,更能够通过稀少和不规律的取样时间反映变异的不确定性。