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 emerging as a sought-after distributed machinelearning architecture, offering the advantage of model training without directexposure of raw data. With advancements in network infrastructure, FL has beenseamlessly integrated into edge computing. However, the limited resources onedge devices introduce security vulnerabilities to FL in the context. Whileblockchain technology promises to bolster security, practical deployment onresource-constrained edge devices remains a challenge. Moreover, theexploration of FL with multiple aggregators in edge computing is still new inthe literature. Addressing these gaps, we introduce the Blockchain-empoweredHeterogeneous Multi-Aggregator Federated Learning Architecture (BMA-FL). Wedesign a novel light-weight Byzantine consensus mechanism, namely PBCM, toenable secure and fast model aggregation and synchronization in BMA-FL. We alsodive into the heterogeneity problem in BMA-FL that the aggregators areassociated with varied number of connected trainers with Non-IID datadistributions and diverse training speed. We proposed a multi-agent deepreinforcement learning algorithm to help aggregators decide the best trainingstrategies. The experiments on real-word datasets demonstrate the efficiency ofBMA-FL to achieve better models faster than baselines, showing the efficacy ofPBCM and proposed deep reinforcement learning algorithm.

A Blockchain-empowered Multi-Aggregator Federated Learning Architecture in Edge Computing with Deep Reinforcement Learning Optimization