UniTS: A Universal Time Series Analysis Framework Powered by Self-Supervised Representation Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liang, Zhiyu, Liang, Chen, Liang, Zheng, Wang, Hongzhi, Zheng, Bo
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917751569776640
author Liang, Zhiyu
Liang, Chen
Liang, Zheng
Wang, Hongzhi
Zheng, Bo
author_facet Liang, Zhiyu
Liang, Chen
Liang, Zheng
Wang, Hongzhi
Zheng, Bo
contents Machine learning has emerged as a powerful tool for time series analysis. Existing methods are usually customized for different analysis tasks and face challenges in tackling practical problems such as partial labeling and domain shift. To improve the performance and address the practical problems universally, we develop UniTS, a novel framework that incorporates self-supervised representation learning (or pre-training). The components of UniTS are designed using sklearn-like APIs to allow flexible extensions. We demonstrate how users can easily perform an analysis task using the user-friendly GUIs, and show the superior performance of UniTS over the traditional task-specific methods without self-supervised pre-training on five mainstream tasks and two practical settings.
format Preprint
id arxiv_https___arxiv_org_abs_2303_13804
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle UniTS: A Universal Time Series Analysis Framework Powered by Self-Supervised Representation Learning
Liang, Zhiyu
Liang, Chen
Liang, Zheng
Wang, Hongzhi
Zheng, Bo
Machine Learning
Databases
Machine learning has emerged as a powerful tool for time series analysis. Existing methods are usually customized for different analysis tasks and face challenges in tackling practical problems such as partial labeling and domain shift. To improve the performance and address the practical problems universally, we develop UniTS, a novel framework that incorporates self-supervised representation learning (or pre-training). The components of UniTS are designed using sklearn-like APIs to allow flexible extensions. We demonstrate how users can easily perform an analysis task using the user-friendly GUIs, and show the superior performance of UniTS over the traditional task-specific methods without self-supervised pre-training on five mainstream tasks and two practical settings.
title UniTS: A Universal Time Series Analysis Framework Powered by Self-Supervised Representation Learning
topic Machine Learning
Databases
url https://arxiv.org/abs/2303.13804