Universal Time-Series Representation Learning: A Survey

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Trirat, Patara, Shin, Yooju, Kang, Junhyeok, Nam, Youngeun, Na, Jihye, Bae, Minyoung, Kim, Joeun, Kim, Byunghyun, Lee, Jae-Gil
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916018834636800
author Trirat, Patara
Shin, Yooju
Kang, Junhyeok
Nam, Youngeun
Na, Jihye
Bae, Minyoung
Kim, Joeun
Kim, Byunghyun
Lee, Jae-Gil
author_facet Trirat, Patara
Shin, Yooju
Kang, Junhyeok
Nam, Youngeun
Na, Jihye
Bae, Minyoung
Kim, Joeun
Kim, Byunghyun
Lee, Jae-Gil
contents Time-series data exists in every corner of real-world systems and services, ranging from satellites in the sky to wearable devices on human bodies. Learning representations by extracting and inferring valuable information from these time series is crucial for understanding the complex dynamics of particular phenomena and enabling informed decisions. With the learned representations, we can perform numerous downstream analyses more effectively. Among several approaches, deep learning has demonstrated remarkable performance in extracting hidden patterns and features from time-series data without manual feature engineering. This survey first presents a novel taxonomy based on three fundamental elements in designing state-of-the-art universal representation learning methods for time series. According to the proposed taxonomy, we comprehensively review existing studies and discuss their intuitions and insights into how these methods enhance the quality of learned representations. Finally, as a guideline for future studies, we summarize commonly used experimental setups and datasets and discuss several promising research directions. An up-to-date corresponding resource is available at https://github.com/itouchz/awesome-deep-time-series-representations.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03717
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Universal Time-Series Representation Learning: A Survey
Trirat, Patara
Shin, Yooju
Kang, Junhyeok
Nam, Youngeun
Na, Jihye
Bae, Minyoung
Kim, Joeun
Kim, Byunghyun
Lee, Jae-Gil
Machine Learning
Artificial Intelligence
Time-series data exists in every corner of real-world systems and services, ranging from satellites in the sky to wearable devices on human bodies. Learning representations by extracting and inferring valuable information from these time series is crucial for understanding the complex dynamics of particular phenomena and enabling informed decisions. With the learned representations, we can perform numerous downstream analyses more effectively. Among several approaches, deep learning has demonstrated remarkable performance in extracting hidden patterns and features from time-series data without manual feature engineering. This survey first presents a novel taxonomy based on three fundamental elements in designing state-of-the-art universal representation learning methods for time series. According to the proposed taxonomy, we comprehensively review existing studies and discuss their intuitions and insights into how these methods enhance the quality of learned representations. Finally, as a guideline for future studies, we summarize commonly used experimental setups and datasets and discuss several promising research directions. An up-to-date corresponding resource is available at https://github.com/itouchz/awesome-deep-time-series-representations.
title Universal Time-Series Representation Learning: A Survey
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.03717