时间戳
计算机科学
代表(政治)
系列(地层学)
背景(考古学)
简单(哲学)
时间序列
异常检测
人工智能
特征学习
编码(集合论)
机器学习
数据挖掘
古生物学
哲学
计算机安全
集合(抽象数据类型)
认识论
政治
政治学
法学
生物
程序设计语言
作者
Zhihan Yue,Yujing Wang,Juanyong Duan,Tianmeng Yang,Congrui Huang,Yunhai Tong,Bixiong Xu
标识
DOI:10.1609/aaai.v36i8.20881
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI