TS2Vec: Towards Universal Representation of Time Series
Authors:
Preprint
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.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- SimCSE: Simple Contrastive Learning of Sentence Embeddings2021
- DeepAR: Probabilistic forecasting with autoregressive recurrent networksInternational Journal of Forecasting, 2020
- The UCR time series archiveIEEE/CAA Journal of Automatica Sinica, 2019
- Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series ForecastingElectronics, 2019
- Network Anomaly Detection Based on Wavelet AnalysisEURASIP Journal on Advances in Signal Processing, 2008
- Time Series Analysis, Forecasting, and ControlTechnometrics, 1995