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 received a surge of interest in recent yearsthanks to its benefits in data privacy protection, efficient communication, andparallel data processing. Also, with appropriate algorithmic designs, one couldachieve the desirable linear speedup for convergence effect in FL. However,most existing works on FL are limited to systems with i.i.d. data andcentralized parameter servers and results on decentralized FL withheterogeneous datasets remains limited. Moreover, whether or not the linearspeedup for convergence is achievable under fully decentralized FL with dataheterogeneity remains an open question. In this paper, we address thesechallenges by proposing a new algorithm, called NET-FLEET, for fullydecentralized FL systems with data heterogeneity. The key idea of our algorithmis to enhance the local update scheme in FL (originally intended forcommunication efficiency) by incorporating a recursive gradient correctiontechnique to handle heterogeneous datasets. We show that, under appropriateparameter settings, the proposed NET-FLEET algorithm achieves a linear speedupfor convergence. We further conduct extensive numerical experiments to evaluatethe performance of the proposed NET-FLEET algorithm and verify our theoreticalfindings.

NET-FLEET: Achieving Linear Convergence Speedup for Fully Decentralized Federated Learning with Heterogeneous Data