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

With the proliferation of intelligent mobile devices in wirelessdevice-to-device (D2D) networks, decentralized federated learning (DFL) hasattracted significant interest. Compared to centralized federated learning(CFL), DFL mitigates the risk of central server failures due to communicationbottlenecks. However, DFL faces several challenges, such as the severeheterogeneity of data distributions in diverse environments, and thetransmission outages and package errors caused by the adoption of the UserDatagram Protocol (UDP) in D2D networks. These challenges often degrade theconvergence of training DFL models. To address these challenges, we conduct athorough theoretical convergence analysis for DFL and derive a convergencebound. By defining a novel quantity named unreliable links-aware neighborhooddiscrepancy in this convergence bound, we formulate a tractable optimizationobjective, and develop a novel Topology Learning method considering theRepresentation Discrepancy and Unreliable Links in DFL, named ToLRDUL.Intensive experiments under both feature skew and label skew settings havevalidated the effectiveness of our proposed method, demonstrating improvedconvergence speed and test accuracy, consistent with our theoretical findings.

Topology Learning for Heterogeneous Decentralized Federated Learning over Unreliable D2D Networks