# Learning Timestamp-Level Representations for Time Series with Hierarchical Contrastive Loss

**Authors:** Zhihan Yue, Yujing Wang, Juanyong Duan, Tianmeng Yang, Congrui Huang, Bixiong Xu  
**arXiv:** [2106.10466](https://arxiv.org/abs/2106.10466)  
**Date:** 2021-06-19  
**Summary page:** https://www.summarizepaper.com/fr/paper/2106.10466v1/

## Abstract

This paper presents TS2Vec, a universal framework for learning timestamp-level representations of time series. Unlike existing methods, TS2Vec performs timestamp-wise discrimination, which learns a contextual representation vector directly for each timestamp. We find that the learned representations have superior predictive ability. A linear regression trained on top of the learned representations outperforms previous SOTAs for supervised time series forecasting. Also, the instance-level representations can be simply obtained by applying a max pooling layer on top of learned representations of all timestamps. We conduct extensive experiments on time series classification tasks to evaluate the quality of instance-level representations. As a result, TS2Vec achieves significant improvement compared with existing SOTAs of unsupervised time series representation on 125 UCR datasets and 29 UEA datasets. The source code is publicly available at https://github.com/yuezhihan/ts2vec.