Interpolation-Prediction Networks for Irregularly Sampled Time Series
This work addresses the challenge of analyzing physiological time series data in electronic health records, which are sparse and irregularly sampled, for applications in healthcare.
The paper tackles the problem of supervised learning with sparse and irregularly sampled multivariate time series by proposing a new deep learning architecture that combines a semi-parametric interpolation network with a prediction network, and it shows that this approach outperforms baseline and recent models on classification and regression tasks.
In this paper, we present a new deep learning architecture for addressing the problem of supervised learning with sparse and irregularly sampled multivariate time series. The architecture is based on the use of a semi-parametric interpolation network followed by the application of a prediction network. The interpolation network allows for information to be shared across multiple dimensions of a multivariate time series during the interpolation stage, while any standard deep learning model can be used for the prediction network. This work is motivated by the analysis of physiological time series data in electronic health records, which are sparse, irregularly sampled, and multivariate. We investigate the performance of this architecture on both classification and regression tasks, showing that our approach outperforms a range of baseline and recently proposed models.