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

The scarcity of class-labeled data is a ubiquitous bottleneck in a wide rangeof machine learning problems. While abundant unlabeled data normally exist andprovide a potential solution, it is extremely challenging to exploit them. Inthis paper, we address this problem by leveraging Positive-Unlabeled~(PU)classification and conditional generation with extra unlabeled data\emph{simultaneously}, both of which aim to make full use of agnostic unlabeleddata to improve classification and generation performances. In particular, wepresent a novel training framework to jointly target both PU classification andconditional generation when exposing to extra data, especiallyout-of-distribution unlabeled data, by exploring the interplay between them: 1)enhancing the performance of PU classifiers with the assistance of a novelConditional Generative Adversarial Network~(CGAN) that is robust to noisylabels, 2) leveraging extra data with predicted labels from a PU classifier tohelp the generation. Our key contribution is a Classifier-Noise-InvariantConditional GAN~(CNI-CGAN) that can learn the clean data distribution fromnoisy labels predicted by a PU classifier. Theoretically, we proved the optimalcondition of CNI-CGAN and experimentally, we conducted extensive evaluations ondiverse datasets, verifying the simultaneous improvements on bothclassification and generation.

Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data