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 a privacy-preserving collaborative machine learning paradigm, federatedlearning (FL) has attracted significant interest from academia and the industryalike. To allow each data owner (a.k.a., FL clients) to train a heterogeneousand personalized local model based on its local data distribution, systemresources and requirements on model structure, the field of model-heterogeneouspersonalized federated learning (MHPFL) has emerged. Existing MHPFL approacheseither rely on the availability of a public dataset with specialcharacteristics to facilitate knowledge transfer, incur high computation andcommunication costs, or face potential model leakage risks. To address theselimitations, we propose a model-heterogeneous personalized Federated learningapproach based on feature Extractor Sharing (pFedES). It incorporates a smallhomogeneous feature extractor into each client's heterogeneous local model.Clients train them via the proposed iterative learning method to enable theexchange of global generalized knowledge and local personalized knowledge. Thesmall local homogeneous extractors produced after local training are uploadedto the FL server and for aggregation to facilitate easy knowledge sharing amongclients. We theoretically prove that pFedES can converge over wall-to-walltime. Extensive experiments on two real-world datasets against sixstate-of-the-art methods demonstrate that pFedES builds the most accuratemodel, while incurring low communication and computation costs. Compared withthe best-performing baseline, it achieves 1.61% higher test accuracy, whilereducing communication and computation costs by 99.6% and 82.9%, respectively.

pFedES: Model Heterogeneous Personalized Federated Learning with Feature Extractor Sharing