Learning from Irregularly-Sampled Time Series: A Missing Data Perspective

Steve Li, Benjamin M Marlin,

Abstract Paper

Tue Jul 14 7 a.m. PDT [iCal] [ Join Zoom ]
Tue Jul 14 6 p.m. PDT [iCal] [ Join Zoom ]
Please do not share or post zoom links


Irregularly-sampled time series occur in many domains including healthcare. They can be challenging to model because they do not naturally yield a fixed-dimensional representation as required by many standard machine learning models. In this paper, we consider irregular sampling from the perspective of missing data. We model observed irregularly-sampled time series data as a sequence of index-value pairs sampled from a continuous but unobserved function. We introduce an encoder-decoder framework for learning from such generic indexed sequences. We propose learning methods for this framework based on variational autoencoders and generative adversarial networks. For continuous irregularly-sampled time series, we introduce continuous convolutional layers that can efficiently interface with existing neural network architectures. Experiments show that our models are able to achieve competitive or better classification results on irregularly-sampled multivariate time series compared to recent RNN models while offering significantly faster training times.

Chat is not available.