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) is a new distributed machine learning framework knownfor its benefits on data privacy and communication efficiency. Since fullclient participation in many cases is infeasible due to constrained resources,partial participation FL algorithms have been investigated that proactivelyselect/sample a subset of clients, aiming to achieve learning performance closeto the full participation case. This paper studies a passive partial clientparticipation scenario that is much less well understood, where partialparticipation is a result of external events, namely client dropout, ratherthan a decision of the FL algorithm. We cast FL with client dropout as aspecial case of a larger class of FL problems where clients can submitsubstitute (possibly inaccurate) local model updates. Based on our convergenceanalysis, we develop a new algorithm FL-FDMS that discovers friends of clients(i.e., clients whose data distributions are similar) on-the-fly and usesfriends' local updates as substitutes for the dropout clients, thereby reducingthe substitution error and improving the convergence performance. A complexityreduction mechanism is also incorporated into FL-FDMS, making it boththeoretically sound and practically useful. Experiments on MNIST and CIFAR-10confirmed the superior performance of FL-FDMS in handling client dropout in FL.

Combating Client Dropout in Federated Learning via Friend Model Substitution