Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/155626
Title: Time-series representation learning via temporal and contextual contrasting
Authors: Eldele, Emadeldeen
Mohamed Ragab
Chen, Zhenghua
Wu, Min
Kwoh, Chee Keong
Li, Xiaoli
Guan, Cuntai
Keywords: Engineering::Computer science and engineering
Issue Date: 2021
Source: Eldele, E., Mohamed Ragab, Chen, Z., Wu, M., Kwoh, C. K., Li, X. & Guan, C. (2021). Time-series representation learning via temporal and contextual contrasting. Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21), 2352-2359. https://dx.doi.org/10.24963/ijcai.2021/324
Project: A20H6b0151
C210112046
Abstract: Learning decent representations from unlabeled time-series data with temporal dynamics is a very challenging task. In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC), to learn time-series representation from unlabeled data. First, the raw time-series data are transformed into two different yet correlated views by using weak and strong augmentations. Second, we propose a novel temporal contrasting module to learn robust temporal representations by designing a tough cross-view prediction task. Last, to further learn discriminative representations, we propose a contextual contrasting module built upon the contexts from the temporal contrasting module. It attempts to maximize the similarity among different contexts of the same sample while minimizing similarity among contexts of different samples. Experiments have been carried out on three real-world time-series datasets. The results manifest that training a linear classifier on top of the features learned by our proposed TS-TCC performs comparably with the supervised training. Additionally, our proposed TS-TCC shows high efficiency in few-labeled data and transfer learning scenarios. The code is publicly available at https://github.com/emadeldeen24/TS-TCC.
URI: https://hdl.handle.net/10356/155626
ISBN: 978-0-9992411-9-6
DOI: 10.24963/ijcai.2021/324
DOI (Related Dataset): 10.21979/N9/RMFXOX
10.21979/N9/TITSXU
10.21979/N9/7KGPRI
10.21979/N9/4PZQJ7
Rights: © 2021 International Joint Conferences on Artificial Intelligence. All rights reserved. This paper was published in Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21) and is made available with permission of nternational Joint Conferences on Artificial Intelligence.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
0324.pdf704.56 kBAdobe PDFView/Open

Page view(s)

37
Updated on Jul 2, 2022

Download(s)

7
Updated on Jul 2, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.