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 privacy-preserving paradigm for collaborativelytraining a global model from decentralized clients. However, the performance ofFL is hindered by non-independent and identically distributed (non-IID) dataand device heterogeneity. In this work, we revisit this key challenge throughthe lens of gradient conflicts on the server side. Specifically, we firstinvestigate the gradient conflict phenomenon among multiple clients and revealthat stronger heterogeneity leads to more severe gradient conflicts. To tacklethis issue, we propose FedGH, a simple yet effective method that mitigateslocal drifts through Gradient Harmonization. This technique projects onegradient vector onto the orthogonal plane of the other within conflictingclient pairs. Extensive experiments demonstrate that FedGH consistentlyenhances multiple state-of-the-art FL baselines across diverse benchmarks andnon-IID scenarios. Notably, FedGH yields more significant improvements inscenarios with stronger heterogeneity. As a plug-and-play module, FedGH can beseamlessly integrated into any FL framework without requiring hyperparametertuning.

Tackling the Non-IID Issue in Heterogeneous Federated Learning by Gradient Harmonization