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

Over the past few years, Federated Learning (FL) has become a populardistributed machine learning paradigm. FL involves a group of clients withdecentralized data who collaborate to learn a common model under thecoordination of a centralized server, with the goal of protecting clients'privacy by ensuring that local datasets never leave the clients and that theserver only performs model aggregation. However, in realistic scenarios, theserver may be able to collect a small amount of data that approximately mimicsthe population distribution and has stronger computational ability to performthe learning process. To address this, we focus on the hybrid FL framework inthis paper. While previous hybrid FL work has shown that the alternativetraining of clients and server can increase convergence speed, it has focusedon the scenario where clients fully participate and ignores the negative effectof partial participation. In this paper, we provide theoretical analysis ofhybrid FL under clients' partial participation to validate that partialparticipation is the key constraint on convergence speed. We then propose a newalgorithm called FedCLG, which investigates the two-fold role of the server inhybrid FL. Firstly, the server needs to process the training steps using itssmall amount of local datasets. Secondly, the server's calculated gradientneeds to guide the participated clients' training and the server's aggregation.We validate our theoretical findings through numerical experiments, which showthat our proposed method FedCLG outperforms state-of-the-art methods.

Accelerating Hybrid Federated Learning Convergence under Partial Participation