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

Conventional centralised deep learning paradigms are not feasible when datafrom different sources cannot be shared due to data privacy or transmissionlimitation. To resolve this problem, federated learning has been introduced totransfer knowledge across multiple sources (clients) with non-shared data whileoptimising a globally generalised central model (server). Existing federatedlearning paradigms mostly focus on transferring holistic high-level knowledge(such as class) across models, which are closely related to specific objects ofinterest so may suffer from inverse attack. In contrast, in this work, weconsider transferring mid-level semantic knowledge (such as attribute) which isnot sensitive to specific objects of interest and therefore is moreprivacy-preserving and scalable. To this end, we formulate a new FederatedZero-Shot Learning (FZSL) paradigm to learn mid-level semantic knowledge atmultiple local clients with non-shared local data and cumulatively aggregate aglobally generalised central model for deployment. To improve modeldiscriminative ability, we propose to explore semantic knowledge augmentationfrom external knowledge for enriching the mid-level semantic space in FZSL.Extensive experiments on five zeroshot learning benchmark datasets validate theeffectiveness of our approach for optimising a generalisable federated learningmodel with mid-level semantic knowledge transfer.

Exploring Semantic Attributes from A Foundation Model for Federated Learning of Disjoint Label Spaces