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

Foundation models have recently gained attention within the field of machinelearning thanks to its efficiency in broad data processing. While researchershad attempted to extend this success to time series models, the main challengeis effectively extracting representations and transferring knowledge frompretraining datasets to the target finetuning dataset. To tackle this issue, weintroduce a novel pretraining procedure that leverages supervised contrastivelearning to distinguish features within each pretraining dataset. Thispretraining phase enables a probabilistic similarity metric, which assesses thelikelihood of a univariate sample being closely related to one of thepretraining datasets. Subsequently, using this similarity metric as a guide, wepropose a fine-tuning procedure designed to enhance the accurate prediction ofthe target data by aligning it more closely with the learned dynamics of thepretraining datasets. Our experiments have shown promising results whichdemonstrate the efficacy of our approach.

A Supervised Contrastive Learning Pretrain-Finetune Approach for Time Series