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

The statistical heterogeneity of the non-independent and identicallydistributed (non-IID) data in local clients significantly limits theperformance of federated learning. Previous attempts like FedProx, SCAFFOLD,MOON, FedNova and FedDyn resort to an optimization perspective, which requiresan auxiliary term or re-weights local updates to calibrate the learning bias orthe objective inconsistency. However, in addition to previous explorations forimprovement in federated averaging, our analysis shows that another criticalbottleneck is the poorer optima of client models in more heterogeneousconditions. We thus introduce a data-driven approach called FedSkip to improvethe client optima by periodically skipping federated averaging and scatteringlocal models to the cross devices. We provide theoretical analysis of thepossible benefit from FedSkip and conduct extensive experiments on a range ofdatasets to demonstrate that FedSkip achieves much higher accuracy, betteraggregation efficiency and competing communication efficiency. Source code isavailable at: https://github.com/MediaBrain-SJTU/FedSkip.

FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation