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) is a way for machines to learn from data that is keptlocally, in order to protect the privacy of clients. This is typically doneusing local SGD, which helps to improve communication efficiency. However, sucha scheme is currently constrained by slow and unstable convergence due to thevariety of data on different clients' devices. In this work, we identify threeunder-explored phenomena of biased local learning that may explain thesechallenges caused by local updates in supervised FL. As a remedy, we proposeFedBR, a novel unified algorithm that reduces the local learning bias onfeatures and classifiers to tackle these challenges. FedBR has two components.The first component helps to reduce bias in local classifiers by balancing theoutput of the models. The second component helps to learn local features thatare similar to global features, but different from those learned from otherdata sources. We conducted several experiments to test \algopt and found thatit consistently outperforms other SOTA FL methods. Both of its components alsoindividually show performance gains. Our code is available athttps://github.com/lins-lab/fedbr.

FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction