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) achieves collaborative learning without the need fordata sharing, thus preventing privacy leakage. To extend FL into a fullydecentralized algorithm, researchers have applied distributed optimizationalgorithms to FL by considering machine learning (ML) tasks as parameteroptimization problems. Conversely, the consensus-based multi-hop federateddistillation (CMFD) proposed in the authors' previous work makes neural network(NN) models get close with others in a function space rather than in aparameter space. Hence, this study solves two unresolved challenges of CMFD:(1) communication cost reduction and (2) visualization of model convergence.Based on a proposed dynamic communication cost reduction method (DCCR), theamount of data transferred in a network is reduced; however, with a slightdegradation in the prediction accuracy. In addition, a technique forvisualizing the distance between the NN models in a function space is alsoproposed. The technique applies a dimensionality reduction technique byapproximating infinite-dimensional functions as numerical vectors to visualizethe trajectory of how the models change by the distributed learning algorithm.

Convergence Visualizer of Decentralized Federated Distillation with Reduced Communication Costs