TS2Vec: Towards Universal Representation of Time Series

Abstract

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.

Appears in AAAI-2022

Cited by in corpus (5)

• TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting
• A Co-training Approach for Noisy Time Series Learning
• Automatic Feature Engineering for Time Series Classification: Evaluation and Discussion
• Full Scaling Automation for Sustainable Development of Green Data Centers
• T-Rep: Representation Learning for Time Series using Time-Embeddings