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) has emerged as a promising privacy-preservingdistributed machine learning framework recently. It aims at collaborativelylearning a shared global model by performing distributed training locally onedge devices and aggregating local models into a global one without centralizedraw data sharing in the cloud server. However, due to the large local dataheterogeneities (Non-I.I.D. data) across edge devices, the FL may easily obtaina global model that can produce more shifted gradients on local datasets,thereby degrading the model performance or even suffering from thenon-convergence during training. In this paper, we propose a novel FL trainingframework, dubbed Fed-FSNet, using a properly designed Fuzzy SynthesizingNetwork (FSNet) to mitigate the Non-I.I.D. FL at-the-source. Concretely, wemaintain an edge-agnostic hidden model in the cloud server to estimate aless-accurate while direction-aware inversion of the global model. The hiddenmodel can then fuzzily synthesize several mimic I.I.D. data samples (samplefeatures) conditioned on only the global model, which can be shared by edgedevices to facilitate the FL training towards faster and better convergence.Moreover, since the synthesizing process involves neither access to theparameters/updates of local models nor analyzing individual local modeloutputs, our framework can still ensure the privacy of FL. Experimental resultson several FL benchmarks demonstrate that our method can significantly mitigatethe Non-I.I.D. issue and obtain better performance against other representativemethods.

Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network