Continuous-time Autoencoders for Regular and Irregular Time Series Imputation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wi, Hyowon, Shin, Yehjin, Park, Noseong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911930173620224
author Wi, Hyowon
Shin, Yehjin
Park, Noseong
author_facet Wi, Hyowon
Shin, Yehjin
Park, Noseong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_16581
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Continuous-time Autoencoders for Regular and Irregular Time Series Imputation
Wi, Hyowon
Shin, Yehjin
Park, Noseong
Machine Learning
Information Retrieval
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.
title Continuous-time Autoencoders for Regular and Irregular Time Series Imputation
topic Machine Learning
Information Retrieval
url https://arxiv.org/abs/2312.16581