English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent studies have shown great promise in unsupervised representationlearning (URL) for multivariate time series, because URL has the capability inlearning generalizable representation for many downstream tasks without usinginaccessible labels. However, existing approaches usually adopt the modelsoriginally designed for other domains (e.g., computer vision) to encode thetime series data and rely on strong assumptions to design learning objectives,which limits their ability to perform well. To deal with these problems, wepropose a novel URL framework for multivariate time series by learningtime-series-specific shapelet-based representation through a popularcontrasting learning paradigm. To the best of our knowledge, this is the firstwork that explores the shapelet-based embedding in the unsupervisedgeneral-purpose representation learning. A unified shapelet-based encoder and anovel learning objective with multi-grained contrasting and multi-scalealignment are particularly designed to achieve our goal, and a dataaugmentation library is employed to improve the generalization. We conductextensive experiments using tens of real-world datasets to assess therepresentation quality on many downstream tasks, including classification,clustering, and anomaly detection. The results demonstrate the superiority ofour method against not only URL competitors, but also techniques speciallydesigned for downstream tasks. Our code has been made publicly available athttps://github.com/real2fish/CSL.

Contrastive Shapelet Learning for Unsupervised Multivariate Time Series Representation Learning