DeepAI
Log In Sign Up

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

08/17/2020
by   Steven Cheng-Xian Li, et al.
0

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.

READ FULL TEXT

page 3

page 7

01/25/2021

Multi-Time Attention Networks for Irregularly Sampled Time Series

Irregular sampling occurs in many time series modeling applications wher...
10/23/2020

A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data

Irregularly sampled time series (ISTS) data has irregular temporal inter...
10/19/2022

Irregularly-Sampled Time Series Modeling with Spline Networks

Observations made in continuous time are often irregular and contain the...
10/21/2020

Probabilistic Numeric Convolutional Neural Networks

Continuous input signals like images and time series that are irregularl...
03/20/2020

Improving Irregularly Sampled Time Series Learning with Dense Descriptors of Time

Supervised learning with irregularly sampled time series have been a cha...
10/01/2019

End-to-end learning of energy-based representations for irregularly-sampled signals and images

For numerous domains, including for instance earth observation, medical ...
09/26/2019

Set Functions for Time Series

Despite the eminent successes of deep neural networks, many architecture...