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

As an exemplary self-supervised approach for representation learning,time-series contrastive learning has exhibited remarkable advancements incontemporary research. While recent contrastive learning strategies havefocused on how to construct appropriate positives and negatives, in this study,we conduct theoretical analysis and find they have overlooked the fundamentalissues: false negatives and class imbalance inherent in the InfoNCE loss-basedframework. Therefore, we introduce a straightforward modification grounded inthe SimCLR framework, universally adaptable to models engaged in the instancediscrimination task. By constructing instance graphs to facilitate interactivelearning among instances, we emulate supervised contrastive learning via themultiple-instances discrimination task, mitigating the harmful impact of falsenegatives. Moreover, leveraging the graph structure and few-labeled data, weperform semi-supervised consistency classification and enhance therepresentative ability of minority classes. We compared our method with themost popular time-series contrastive learning methods on four real-worldtime-series datasets and demonstrated our significant advantages in overallperformance.

Time-Series Contrastive Learning against False Negatives and Class Imbalance