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

Cross-device Federated Learning (FL) faces significant challenges wherelow-end clients that could potentially make unique contributions are excludedfrom training large models due to their resource bottlenecks. Recent researchefforts have focused on model-heterogeneous FL, by extracting reduced-sizemodels from the global model and applying them to local clients accordingly.Despite the empirical success, general theoretical guarantees of convergence onthis method remain an open question. This paper presents a unifying frameworkfor heterogeneous FL algorithms with online model extraction and provides ageneral convergence analysis for the first time. In particular, we prove thatunder certain sufficient conditions and for both IID and non-IID data, thesealgorithms converge to a stationary point of standard FL for general smoothcost functions. Moreover, we introduce the concept of minimum coverage index,together with model reduction noise, which will determine the convergence ofheterogeneous federated learning, and therefore we advocate for a holisticapproach that considers both factors to enhance the efficiency of heterogeneousfederated learning.

Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction