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

Training Deep Learning (DL) models require large, high-quality datasets,often assembled with data from different institutions. Federated Learning (FL)has been emerging as a method for privacy-preserving pooling of datasetsemploying collaborative training from different institutions by iterativelyglobally aggregating locally trained models. One critical performance challengeof FL is operating on datasets not independently and identically distributed(non-IID) among the federation participants. Even though this fragility cannotbe eliminated, it can be debunked by a suitable optimization of twohyper-parameters: layer normalization methods and collaboration frequencyselection. In this work, we benchmark five different normalization layers fortraining Neural Networks (NNs), two families of non-IID data skew, and twodatasets. Results show that Batch Normalization, widely employed forcentralized DL, is not the best choice for FL, whereas Group and LayerNormalization consistently outperform Batch Normalization. Similarly, frequentmodel aggregation decreases convergence speed and mode quality.

Experimenting with Normalization Layers in Federated Learning on non-IID scenarios