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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Learning semantic-rich representations from raw unlabeled time series data iscritical for downstream tasks such as classification and forecasting.Contrastive learning has recently shown its promising representation learningcapability in the absence of expert annotations. However, existing contrastiveapproaches generally treat each instance independently, which leads to falsenegative pairs that share the same semantics. To tackle this problem, wepropose MHCCL, a Masked Hierarchical Cluster-wise Contrastive Learning model,which exploits semantic information obtained from the hierarchical structureconsisting of multiple latent partitions for multivariate time series.Motivated by the observation that fine-grained clustering preserves higherpurity while coarse-grained one reflects higher-level semantics, we propose anovel downward masking strategy to filter out fake negatives and supplementpositives by incorporating the multi-granularity information from theclustering hierarchy. In addition, a novel upward masking strategy is designedin MHCCL to remove outliers of clusters at each partition to refine prototypes,which helps speed up the hierarchical clustering process and improves theclustering quality. We conduct experimental evaluations on seven widely-usedmultivariate time series datasets. The results demonstrate the superiority ofMHCCL over the state-of-the-art approaches for unsupervised time seriesrepresentation learning.

MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series