Universal Time-Series Representation Learning: A Survey
ACM Computing Surveys · 30.09.2026 · 58 (12) · 1-40
DOI: 10.1145/3817600 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 09.06.2026. Verfasst von Patara Trirat und 8 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 242 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation, High-Usability and Performance In-Memory Distributed DBMS for Deep Learning.
Abstract (Originalsprache)
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.
Förderung
- Institute of Information & Communications Technology Planning & Evaluation
- High-Usability and Performance In-Memory Distributed DBMS for Deep Learning
Zitieren
APA
Trirat, P., Shin, Y., Kang, J., Nam, Y., Na, J., Bae, M., Kim, J., Kim, B., & Lee, J. (2026). Universal Time-Series Representation Learning: A Survey. ACM Computing Surveys, 58(12), 1-40. https://doi.org/10.1145/3817600
Vancouver
Trirat P, Shin Y, Kang J, Nam Y, Na J, Bae M, et al. Universal Time-Series Representation Learning: A Survey. ACM Computing Surveys. 2026;58(12):1-40. doi:10.1145/3817600
BibTeX
@article{Trirat2026,
author = {Trirat, Patara and Shin, Yooju and Kang, Junhyeok and Nam, Youngeun and Na, Jihye and Bae, Minyoung and Kim, Joeun and Kim, Byunghyun and Lee, Jae-Gil},
title = {Universal Time-Series Representation Learning: A Survey},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {12},
pages = {1--40},
doi = {10.1145/3817600}
}
EUVIMED