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

by   Zhihan Yue, et al.

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.


page 1

page 2

page 3

page 4


Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification

Learning time-series representations when only unlabeled data or few lab...

A 1d convolutional network for leaf and time series classification

In this paper, a 1d convolutional neural network is designed for classif...

Time-Series Representation Learning via Temporal and Contextual Contrasting

Learning decent representations from unlabeled time-series data with tem...

Contrastive Shapelet Learning for Unsupervised Multivariate Time Series Representation Learning

Recent studies have shown great promise in unsupervised representation l...

Correlated Time Series Self-Supervised Representation Learning via Spatiotemporal Bootstrapping

Correlated time series analysis plays an important role in many real-wor...

Machine Learning vs Statistical Methods for Time Series Forecasting: Size Matters

Time series forecasting is one of the most active research topics. Machi...

WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series Tasks

Machine learning models often fail to generalize well under distribution...

Code Repositories


A universal framework for learning timestamp-level representations of time series

view repo

Please sign up or login with your details

Forgot password? Click here to reset