Multi-Time Attention Networks for Irregularly Sampled Time Series
This addresses the problem of handling sparse, irregular time series for applications like healthcare data analysis, representing an incremental improvement over existing methods.
The authors tackled the challenge of modeling irregularly sampled time series, such as physiological data from electronic health records, by proposing Multi-Time Attention Networks, which learn continuous-time embeddings and use attention to create fixed-length representations. Their results show the approach performs as well or better than baselines and recent models, with significantly faster training times.
Irregular sampling occurs in many time series modeling applications where it presents a significant challenge to standard deep learning models. This work is motivated by the analysis of physiological time series data in electronic health records, which are sparse, irregularly sampled, and multivariate. In this paper, we propose a new deep learning framework for this setting that we call Multi-Time Attention Networks. Multi-Time Attention Networks learn an embedding of continuous-time values and use an attention mechanism to produce a fixed-length representation of a time series containing a variable number of observations. We investigate the performance of this framework on interpolation and classification tasks using multiple datasets. Our results show that the proposed approach performs as well or better than a range of baseline and recently proposed models while offering significantly faster training times than current state-of-the-art methods.