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

Federated learning (FL) is a promising approach for enhancing data privacypreservation, particularly for authentication systems. However, limited roundcommunications, scarce representation, and scalability pose significantchallenges to its deployment, hindering its full potential. In this paper, wepropose 'ProtoFL', Prototypical Representation Distillation based unsupervisedFederated Learning to enhance the representation power of a global model andreduce round communication costs. Additionally, we introduce a local one-classclassifier based on normalizing flows to improve performance with limited data.Our study represents the first investigation of using FL to improve one-classclassification performance. We conduct extensive experiments on five widelyused benchmarks, namely MNIST, CIFAR-10, CIFAR-100, ImageNet-30, andKeystroke-Dynamics, to demonstrate the superior performance of our proposedframework over previous methods in the literature.

ProtoFL: Unsupervised Federated Learning via Prototypical Distillation