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 is an important framework in modern machine learning thatseeks to integrate the training of learning models from multiple users, eachuser having their own local data set, in a way that is sensitive to dataprivacy and to communication loss constraints. In clustered federated learning,one assumes an additional unknown group structure among users, and the goal isto train models that are useful for each group, rather than simply training asingle global model for all users. In this paper, we propose a novel solutionto the problem of clustered federated learning that is inspired by ideas inconsensus-based optimization (CBO). Our new CBO-type method is based on asystem of interacting particles that is oblivious to group memberships. Ourmodel is motivated by rigorous mathematical reasoning, including a mean fieldanalysis describing the large number of particles limit of our particle system,as well as convergence guarantees for the simultaneous global optimization ofgeneral non-convex objective functions (corresponding to the loss functions ofeach cluster of users) in the mean-field regime. Experimental resultsdemonstrate the efficacy of our FedCBO algorithm compared to otherstate-of-the-art methods and help validate our methodological and theoreticalwork.

FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization