Time-series representation learning via temporal and contextual contrasting

• Main Authors: Eldele, Emadeldeen, Mohamed Ragab, Chen, Zhenghua, Wu, Min, Kwoh, Chee Keong, Li, Xiaoli, Guan, Cuntai
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering; Deep Learning; Semi-Supervised Learning; Time-Series; Machine Learning
• Online Access: https://hdl.handle.net/10356/155626
• Institution: Nanyang Technological University

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 unlabe...