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) supports distributed training of a global machinelearning model across multiple devices with the help of a central server.However, data heterogeneity across different devices leads to the client modeldrift issue and results in model performance degradation and poor modelfairness. To address the issue, we design Federated learning with global-localKnowledge Fusion (FedKF) scheme in this paper. The key idea in FedKF is to letthe server return the global knowledge to be fused with the local knowledge ineach training round so that the local model can be regularized towards theglobal optima. Therefore, the client model drift issue can be mitigated. InFedKF, we first propose the active-inactive model aggregation technique thatsupports a precise global knowledge representation. Then, we propose adata-free knowledge distillation (KD) approach to enable each client model tolearn the global knowledge (embedded in the global model) while each clientmodel can still learn the local knowledge (embedded in the local dataset)simultaneously, thereby realizing the global-local knowledge fusion process.The theoretical analysis and intensive experiments demonstrate the superiorityof FedKF over previous solutions.

Handling Data Heterogeneity in Federated Learning via Knowledge Distillation and Fusion