Interpolation-Prediction Networks for Irregularly Sampled Time Series

TL;DR

This paper introduces a novel deep learning architecture combining semi-parametric interpolation and prediction networks to effectively model sparse, irregularly sampled multivariate time series, particularly in healthcare data.

Contribution

The paper proposes a new architecture that integrates shared interpolation across multiple dimensions with flexible prediction models for irregular time series.

Findings

Outperforms existing models on classification tasks.

Effective on sparse, irregularly sampled physiological data.

Applicable to both regression and classification problems.

Abstract

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.