TS2Vec: Towards Universal Representation of Time Series

This paper presents TS2Vec, a universal framework for learning representations of time series in an arbitrary semantic level. Unlike existing methods, TS2Vec performs contrastive learning in a hierarchical way over augmented context views, which enables a robust contextual representation for each timestamp. Furthermore, to obtain the representation of an arbitrary sub-sequence in the time series, we can apply a simple aggregation over the representations of corresponding timestamps. We conduct extensive experiments on time series classification tasks to evaluate the quality of time series representations. As a result, TS2Vec achieves significant improvement over existing SOTAs of unsupervised time series representation on 125 UCR datasets and 29 UEA datasets. The learned timestamp-level representations also achieve superior results in time series forecasting and anomaly detection tasks. A linear regression trained on top of the learned representations outperforms previous SOTAs of time series forecasting. Furthermore, we present a simple way to apply the learned representations for unsupervised anomaly detection, which establishes SOTA results in the literature. The source code is publicly available at https: //github. com/yuezhihan/ts2vec.

Authors

• Zhihan Yue
• Yujing Wang Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing School of Artificial Intelligence, Beihang University, China
• Juanyong Duan
• Tianmeng Yang
• Congrui Huang
• Yunhai Tong Peking University
• Bixiong Xu

Keywords

No keywords are indexed for this paper.