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

In this paper, to deal with the heterogeneity in federated learning (FL)systems, a knowledge distillation (KD) driven training framework for FL isproposed, where each user can select its neural network model on demand anddistill knowledge from a big teacher model using its own private dataset. Toovercome the challenge of train the big teacher model in resource limited userdevices, the digital twin (DT) is exploit in the way that the teacher model canbe trained at DT located in the server with enough computing resources. Then,during model distillation, each user can update the parameters of its model ateither the physical entity or the digital agent. The joint problem of modelselection and training offloading and resource allocation for users isformulated as a mixed integer programming (MIP) problem. To solve the problem,Q-learning and optimization are jointly used, where Q-learning selects modelsfor users and determines whether to train locally or on the server, andoptimization is used to allocate resources for users based on the output ofQ-learning. Simulation results show the proposed DT-assisted KD framework andjoint optimization method can significantly improve the average accuracy ofusers while reducing the total delay.

Digital Twin-Assisted Knowledge Distillation Framework for Heterogeneous Federated Learning