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), as a rapidly evolving privacy-preservingcollaborative machine learning paradigm, is a promising approach to enable edgeintelligence in the emerging Industrial Metaverse. Even though many successfuluse cases have proved the feasibility of FL in theory, in the industrialpractice of Metaverse, the problems of non-independent and identicallydistributed (non-i.i.d.) data, learning forgetting caused by streamingindustrial data, and scarce communication bandwidth remain key barriers torealize practical FL. Facing the above three challenges simultaneously, thispaper presents a high-performance and efficient system named HFEDMS forincorporating practical FL into Industrial Metaverse. HFEDMS reduces dataheterogeneity through dynamic grouping and training mode conversion (DynamicSequential-to-Parallel Training, STP). Then, it compensates for the forgottenknowledge by fusing compressed historical data semantics and calibratesclassifier parameters (Semantic Compression and Compensation, SCC). Finally,the network parameters of the feature extractor and classifier are synchronizedin different frequencies (Layer-wiseAlternative Synchronization Protocol, LASP)to reduce communication costs. These techniques make FL more adaptable to theheterogeneous streaming data continuously generated by industrial equipment,and are also more efficient in communication than traditional methods (e.g.,Federated Averaging). Extensive experiments have been conducted on the streamednon-i.i.d. FEMNIST dataset using 368 simulated devices. Numerical results showthat HFEDMS improves the classification accuracy by at least 6.4% compared with8 benchmarks and saves both the overall runtime and transfer bytes by up to98%, proving its superiority in precision and efficiency.

HFedMS: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaverse