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/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Multi-label classification has attracted an increasing amount of attention inrecent years. To this end, many algorithms have been developed to classifymulti-label data in an effective manner. However, they usually do not considerthe pairwise relations indicated by sample labels, which actually playimportant roles in multi-label classification. Inspired by this, we naturallyextend the traditional pairwise constraints to the multi-label scenario via aflexible thresholding scheme. Moreover, to improve the generalization abilityof the classifier, we adopt a boosting-like strategy to construct a multi-labelensemble from a group of base classifiers. To achieve these goals, this paperpresents a novel multi-label classification framework named Variable PairwiseConstraint projection for Multi-label Ensemble (VPCME). Specifically, we takeadvantage of the variable pairwise constraint projection to learn alower-dimensional data representation, which preserves the correlations betweensamples and labels. Thereafter, the base classifiers are trained in the newdata space. For the boosting-like strategy, we employ both the variablepairwise constraints and the bootstrap steps to diversify the base classifiers.Empirical studies have shown the superiority of the proposed method incomparison with other approaches.

Multi-label ensemble based on variable pairwise constraint projection