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) inevitably confronts the challenge of systemheterogeneity in practical scenarios. To enhance the capabilities of mostmodel-homogeneous FL methods in handling system heterogeneity, we propose atraining scheme that can extend their capabilities to cope with this challenge.In this paper, we commence our study with a detailed exploration of homogeneousand heterogeneous FL settings and discover three key observations: (1) apositive correlation between client performance and layer similarities, (2)higher similarities in the shallow layers in contrast to the deep layers, and(3) the smoother gradients distributions indicate the higher layersimilarities. Building upon these observations, we propose InCo Aggregationthat leverags internal cross-layer gradients, a mixture of gradients fromshallow and deep layers within a server model, to augment the similarity in thedeep layers without requiring additional communication between clients.Furthermore, our methods can be tailored to accommodate model-homogeneous FLmethods such as FedAvg, FedProx, FedNova, Scaffold, and MOON, to expand theircapabilities to handle the system heterogeneity. Copious experimental resultsvalidate the effectiveness of InCo Aggregation, spotlighting internalcross-layer gradients as a promising avenue to enhance the performance inheterogenous FL.

Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning