Bayesian Continual Imputation and Prediction For Irregularly Sampled Time Series Data

Yang Guo; Jeanette Wen Jun Poh; Cheryl Sze Yin Wong; Savitha Ramasamy

ICASSP 2022accepted0 citations

Bayesian Continual Imputation and Prediction For Irregularly Sampled Time Series Data

Yang Guo, Jeanette Wen Jun Poh, Cheryl Sze Yin Wong, Savitha Ramasamy

Abstract

Learning from irregularly sampled, streaming, multi-variate time-series data with many missing values is a very challenging task. In this paper, we propose a Bayesian Continual Imputation and Prediction for Time-series Data (B-CIPIT), for learning from a sequence of time-series tasks. First, we develop a Bayesian LSTM based continual learning algorithm, which is capable of learning continually from a sequence of multi-variate time-series tasks, without catastrophically forgetting any representations. Second, we impute missing values in these time-series sequences, in a continual learning setting. We demonstrate and evaluate the robustness of the proposed algorithm on two real-world clinical time-series data sets, namely MIMIC-III [1] and PhysioNet Challenge 2012 [2]. Performance study results show the superiority of the proposed learning algorithm.

BibTeX

@inproceedings{icassp2022_bayesiancontinua,
  title = {Bayesian Continual Imputation and Prediction For Irregularly Sampled Time Series Data},
  author = {Yang Guo and Jeanette Wen Jun Poh and Cheryl Sze Yin Wong and Savitha Ramasamy},
  booktitle = {ICASSP 2022},
  year = {2022}
}