Set Functions for Time Series

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.

arXiv commentAccepted at the International Conference on Machine Learning (ICML) 2020

References in corpus (7)

• ReZero is All You Need: Fast Convergence at Large Depth
• Deep Kalman Filters
• Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier
• A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification
• Interpolation-Prediction Networks for Irregularly Sampled Time Series
• Joint Modeling of Event Sequence and Time Series with Attentional Twin Recurrent Neural Networks
• Temporal-Clustering Invariance in Irregular Healthcare Time Series

Cited by in corpus (3)

• Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series
• Probabilistic Numeric Convolutional Neural Networks
• Path Imputation Strategies for Signature Models of Irregular Time Series