Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378945243> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4378945243 abstract "Recent studies have shown great promise in unsupervised representation learning (URL) for multivariate time series, because URL has the capability in learning generalizable representation for many downstream tasks without using inaccessible labels. However, existing approaches usually adopt the models originally designed for other domains (e.g., computer vision) to encode the time series data and rely on strong assumptions to design learning objectives, which limits their ability to perform well. To deal with these problems, we propose a novel URL framework for multivariate time series by learning time-series-specific shapelet-based representation through a popular contrasting learning paradigm. To the best of our knowledge, this is the first work that explores the shapelet-based embedding in the unsupervised general-purpose representation learning. A unified shapelet-based encoder and a novel learning objective with multi-grained contrasting and multi-scale alignment are particularly designed to achieve our goal, and a data augmentation library is employed to improve the generalization. We conduct extensive experiments using tens of real-world datasets to assess the representation quality on many downstream tasks, including classification, clustering, and anomaly detection. The results demonstrate the superiority of our method against not only URL competitors, but also techniques specially designed for downstream tasks. Our code has been made publicly available at https://github.com/real2fish/CSL." @default.
- W4378945243 created "2023-06-01" @default.
- W4378945243 creator A5009221204 @default.
- W4378945243 creator A5035113720 @default.
- W4378945243 creator A5043975539 @default.
- W4378945243 creator A5047244598 @default.
- W4378945243 creator A5049301997 @default.
- W4378945243 creator A5075227410 @default.
- W4378945243 date "2023-05-30" @default.
- W4378945243 modified "2023-09-28" @default.
- W4378945243 title "Contrastive Shapelet Learning for Unsupervised Multivariate Time Series Representation Learning" @default.
- W4378945243 doi "https://doi.org/10.48550/arxiv.2305.18888" @default.
- W4378945243 hasPublicationYear "2023" @default.
- W4378945243 type Work @default.
- W4378945243 citedByCount "0" @default.
- W4378945243 crossrefType "posted-content" @default.
- W4378945243 hasAuthorship W4378945243A5009221204 @default.
- W4378945243 hasAuthorship W4378945243A5035113720 @default.
- W4378945243 hasAuthorship W4378945243A5043975539 @default.
- W4378945243 hasAuthorship W4378945243A5047244598 @default.
- W4378945243 hasAuthorship W4378945243A5049301997 @default.
- W4378945243 hasAuthorship W4378945243A5075227410 @default.
- W4378945243 hasBestOaLocation W43789452431 @default.
- W4378945243 hasConcept C101738243 @default.
- W4378945243 hasConcept C104317684 @default.
- W4378945243 hasConcept C108583219 @default.
- W4378945243 hasConcept C119857082 @default.
- W4378945243 hasConcept C124101348 @default.
- W4378945243 hasConcept C134306372 @default.
- W4378945243 hasConcept C154945302 @default.
- W4378945243 hasConcept C161584116 @default.
- W4378945243 hasConcept C177148314 @default.
- W4378945243 hasConcept C17744445 @default.
- W4378945243 hasConcept C185592680 @default.
- W4378945243 hasConcept C199539241 @default.
- W4378945243 hasConcept C2776359362 @default.
- W4378945243 hasConcept C33923547 @default.
- W4378945243 hasConcept C41008148 @default.
- W4378945243 hasConcept C41608201 @default.
- W4378945243 hasConcept C55493867 @default.
- W4378945243 hasConcept C59404180 @default.
- W4378945243 hasConcept C66746571 @default.
- W4378945243 hasConcept C73555534 @default.
- W4378945243 hasConcept C739882 @default.
- W4378945243 hasConcept C8038995 @default.
- W4378945243 hasConcept C94625758 @default.
- W4378945243 hasConceptScore W4378945243C101738243 @default.
- W4378945243 hasConceptScore W4378945243C104317684 @default.
- W4378945243 hasConceptScore W4378945243C108583219 @default.
- W4378945243 hasConceptScore W4378945243C119857082 @default.
- W4378945243 hasConceptScore W4378945243C124101348 @default.
- W4378945243 hasConceptScore W4378945243C134306372 @default.
- W4378945243 hasConceptScore W4378945243C154945302 @default.
- W4378945243 hasConceptScore W4378945243C161584116 @default.
- W4378945243 hasConceptScore W4378945243C177148314 @default.
- W4378945243 hasConceptScore W4378945243C17744445 @default.
- W4378945243 hasConceptScore W4378945243C185592680 @default.
- W4378945243 hasConceptScore W4378945243C199539241 @default.
- W4378945243 hasConceptScore W4378945243C2776359362 @default.
- W4378945243 hasConceptScore W4378945243C33923547 @default.
- W4378945243 hasConceptScore W4378945243C41008148 @default.
- W4378945243 hasConceptScore W4378945243C41608201 @default.
- W4378945243 hasConceptScore W4378945243C55493867 @default.
- W4378945243 hasConceptScore W4378945243C59404180 @default.
- W4378945243 hasConceptScore W4378945243C66746571 @default.
- W4378945243 hasConceptScore W4378945243C73555534 @default.
- W4378945243 hasConceptScore W4378945243C739882 @default.
- W4378945243 hasConceptScore W4378945243C8038995 @default.
- W4378945243 hasConceptScore W4378945243C94625758 @default.
- W4378945243 hasLocation W43789452431 @default.
- W4378945243 hasOpenAccess W4378945243 @default.
- W4378945243 hasPrimaryLocation W43789452431 @default.
- W4378945243 hasRelatedWork W2335364074 @default.
- W4378945243 hasRelatedWork W2784313445 @default.
- W4378945243 hasRelatedWork W2902482704 @default.
- W4378945243 hasRelatedWork W2912933387 @default.
- W4378945243 hasRelatedWork W2931608861 @default.
- W4378945243 hasRelatedWork W2997669297 @default.
- W4378945243 hasRelatedWork W3044458868 @default.
- W4378945243 hasRelatedWork W3197004086 @default.
- W4378945243 hasRelatedWork W4210405904 @default.
- W4378945243 hasRelatedWork W4300480195 @default.
- W4378945243 isParatext "false" @default.
- W4378945243 isRetracted "false" @default.
- W4378945243 workType "article" @default.