English

Continuous-time Autoencoders for Regular and Irregular Time Series Imputation

Machine Learning 2024-06-25 v3 Information Retrieval

Abstract

Time series imputation is one of the most fundamental tasks for time series. Real-world time series datasets are frequently incomplete (or irregular with missing observations), in which case imputation is strongly required. Many different time series imputation methods have been proposed. Recent self-attention-based methods show the state-of-the-art imputation performance. However, it has been overlooked for a long time to design an imputation method based on continuous-time recurrent neural networks (RNNs), i.e., neural controlled differential equations (NCDEs). To this end, we redesign time series (variational) autoencoders based on NCDEs. Our method, called continuous-time autoencoder (CTA), encodes an input time series sample into a continuous hidden path (rather than a hidden vector) and decodes it to reconstruct and impute the input. In our experiments with 4 datasets and 19 baselines, our method shows the best imputation performance in almost all cases.

Keywords

Cite

@article{arxiv.2312.16581,
  title  = {Continuous-time Autoencoders for Regular and Irregular Time Series Imputation},
  author = {Hyowon Wi and Yehjin Shin and Noseong Park},
  journal= {arXiv preprint arXiv:2312.16581},
  year   = {2024}
}

Comments

Published as a WSDM'24 full paper (oral presentation)

R2 v1 2026-06-28T14:03:00.980Z