Series2vec: similarity-based self-supervised representation learning for time series classification
Data Mining and Knowledge Discovery · 2024-07 · 38 (4) · 2520-2544
DOI: 10.1007/s10618-024-01043-w ↗Kurz gefasst
Fachartikel in der Zeitschrift Data Mining and Knowledge Discovery, online erschienen am 20.06.2024. Verfasst von Navid Mohammadi Foumani und 4 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Monash University.
Abstract (Originalsprache)
We argue that time series analysis is fundamentally different in nature to either vision or natural language processing with respect to the forms of meaningful self-supervised learning tasks that can be defined. Motivated by this insight, we introduce a novel approach called Series2Vec for self-supervised representation learning. Unlike the state-of-the-art methods in time series which rely on hand-crafted data augmentation, Series2Vec is trained by predicting the similarity between two series in both temporal and spectral domains through a self-supervised task. By leveraging the similarity prediction task, which has inherent meaning for a wide range of time series analysis tasks, Series2Vec eliminates the need for hand-crafted data augmentation. To further enforce the network to learn similar representations for similar time series, we propose a novel approach that applies order-invariant attention to each representation within the batch during training. Our evaluation of Series2Vec on nine large real-world datasets, along with the UCR/UEA archive, shows enhanced performance compared to current state-of-the-art self-supervised techniques for time series. Additionally, our extensive experiments show that Series2Vec performs comparably with fully supervised training and offers high efficiency in datasets with limited-labeled data. Finally, we show that the fusion of Series2Vec with other representation learning models leads to enhanced performance for time series classification. Code and models are open-source at https://github.com/Navidfoumani/Series2Vec
Förderung
- Monash University
Zitieren
APA
Foumani, N. M., Tan, C. W., Webb, G. I., Rezatofighi, H., & Salehi, M. (2024). Series2vec: similarity-based self-supervised representation learning for time series classification. Data Mining and Knowledge Discovery, 38(4), 2520-2544. https://doi.org/10.1007/s10618-024-01043-w
Vancouver
Foumani NM, Tan CW, Webb GI, Rezatofighi H, Salehi M. Series2vec: similarity-based self-supervised representation learning for time series classification. Data Mining and Knowledge Discovery. 2024;38(4):2520-2544. doi:10.1007/s10618-024-01043-w
BibTeX
@article{Foumani2024,
author = {Foumani, Navid Mohammadi and Tan, Chang Wei and Webb, Geoffrey I. and Rezatofighi, Hamid and Salehi, Mahsa},
title = {Series2vec: similarity-based self-supervised representation learning for time series classification},
journal = {Data Mining and Knowledge Discovery},
year = {2024},
volume = {38},
number = {4},
pages = {2520--2544},
doi = {10.1007/s10618-024-01043-w}
}
EUVIMED