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 an emerging practical framework for effective andscalable machine learning among multiple participants, such as end users,organizations and companies. However, most existing FL or distributed learningframeworks have not well addressed two important issues together: collaborativefairness and adversarial robustness (e.g. free-riders and maliciousparticipants). In conventional FL, all participants receive the global model(equal rewards), which might be unfair to the high-contributing participants.Furthermore, due to the lack of a safeguard mechanism, free-riders or maliciousadversaries could game the system to access the global model for free or tosabotage it. In this paper, we propose a novel Robust and Fair FederatedLearning (RFFL) framework to achieve collaborative fairness and adversarialrobustness simultaneously via a reputation mechanism. RFFL maintains areputation for each participant by examining their contributions via theiruploaded gradients (using vector similarity) and thus identifiesnon-contributing or malicious participants to be removed. Our approachdifferentiates itself by not requiring any auxiliary/validation dataset.Extensive experiments on benchmark datasets show that RFFL can achieve highfairness and is very robust to different types of adversaries while achievingcompetitive predictive accuracy.

A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning