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

Personalized federated learning (FL) aims to train model(s) that can performwell for individual clients that are highly data and system heterogeneous. Mostwork in personalized FL, however, assumes using the same model architecture atall clients and increases the communication cost by sending/receiving models.This may not be feasible for realistic scenarios of FL. In practice, clientshave highly heterogeneous system-capabilities and limited communicationresources. In our work, we propose a personalized FL framework, PerFed-CKT,where clients can use heterogeneous model architectures and do not directlycommunicate their model parameters. PerFed-CKT uses clustered co-distillation,where clients use logits to transfer their knowledge to other clients that havesimilar data-distributions. We theoretically show the convergence andgeneralization properties of PerFed-CKT and empirically show that PerFed-CKTachieves high test accuracy with several orders of magnitude lowercommunication cost compared to the state-of-the-art personalized FL schemes.

Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer