arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.13804cs.LGcs.DB
收藏

UniTS:一种由自监督表示学习驱动的通用时间序列分析框架

UniTS: A Universal Time Series Analysis Framework Powered by Self-Supervised Representation Learning

Harbin Institute of Technology(哈尔滨工业大学);CnosDB Inc.(CnosDB公司)

Zhiyu Liang, Chen Liang, Zheng Liang, Hongzhi Wang, Bo Zheng

AI总结:

针对现有时间序列分析方法任务定制化、难应对部分标注与域偏移等问题,研究提出融合自监督表示学习、类sklearn API且带友好GUI的UniTS通用框架,在多任务和实际场景中性能优于传统任务特定方法。

摘要:

机器学习已成为时间序列分析的强大工具。现有方法通常为不同分析任务定制,在应对部分标注、域偏移等实际问题时面临挑战。为提升性能并通用地解决这些实际问题,我们开发了UniTS,这是一种融合自监督表示学习(即预训练)的新型框架。UniTS的组件采用类sklearn的API设计,支持灵活扩展。我们展示了用户如何通过友好的图形用户界面(GUI)轻松执行分析任务,并证明在五项主流任务和两种实际场景下,UniTS的性能优于无自监督预训练的传统任务特定方法。

英文摘要:

Machine learning has emerged as a powerful tool for time series analysis. Existing methods are usually customized for different analysis tasks and face challenges in tackling practical problems such as partial labeling and domain shift. To improve the performance and address the practical problems universally, we develop UniTS, a novel framework that incorporates self-supervised representation learning (or pre-training). The components of UniTS are designed using sklearn-like APIs to allow flexible extensions. We demonstrate how users can easily perform an analysis task using the user-friendly GUIs, and show the superior performance of UniTS over the traditional task-specific methods without self-supervised pre-training on five mainstream tasks and two practical settings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑