Set Functions for Time Series

TL;DR

This paper introduces SeFT, a scalable and efficient set function-based method for classifying irregularly-sampled time series, particularly in healthcare, with the ability to quantify individual observation contributions.

Contribution

The paper presents SeFT, a novel set function approach that handles irregular time series efficiently and provides interpretability through contribution quantification.

Findings

Performs competitively on healthcare datasets

Reduces runtime significantly compared to existing methods

Scales well to large and long time series datasets

Abstract

Despite the eminent successes of deep neural networks, many architectures are often hard to transfer to irregularly-sampled and asynchronous time series that commonly occur in real-world datasets, especially in healthcare applications. This paper proposes a novel approach for classifying irregularly-sampled time series with unaligned measurements, focusing on high scalability and data efficiency. Our method SeFT (Set Functions for Time Series) is based on recent advances in differentiable set function learning, extremely parallelizable with a beneficial memory footprint, thus scaling well to large datasets of long time series and online monitoring scenarios. Furthermore, our approach permits quantifying per-observation contributions to the classification outcome. We extensively compare our method with existing algorithms on multiple healthcare time series datasets and demonstrate that it performs competitively whilst significantly reducing runtime.