TS2Vec: Towards Universal Representation of Time Series

🤖 Plain-English Summary

This paper presents TS2Vec, a universal framework for learning representations of time series in an arbitrary semantic level. Additionally, we present a simple way to apply the learned representations for unsupervised anomaly detection, which establishes SOTA results in the literature.

🔑 Key Findings

• Unlike existing methods, TS2Vec performs contrastive learning in a hierarchical way over augmented context views, which enables a robust contextual representation for each timestamp.
• Additionally, 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.

🔗 Related Resources