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

One of the key challenges in federated learning (FL) is local datadistribution heterogeneity across clients, which may cause inconsistent featurespaces across clients. To address this issue, we propose a novel method FedFM,which guides each client's features to match shared category-wise anchors(landmarks in feature space). This method attempts to mitigate the negativeeffects of data heterogeneity in FL by aligning each client's feature space.Besides, we tackle the challenge of varying objective function and provideconvergence guarantee for FedFM. In FedFM, to mitigate the phenomenon ofoverlapping feature spaces across categories and enhance the effectiveness offeature matching, we further propose a more precise and effective featurematching loss called contrastive-guiding (CG), which guides each local featureto match with the corresponding anchor while keeping away fromnon-corresponding anchors. Additionally, to achieve higher efficiency andflexibility, we propose a FedFM variant, called FedFM-Lite, where clientscommunicate with server with fewer synchronization times and communicationbandwidth costs. Through extensive experiments, we demonstrate that FedFM withCG outperforms several works by quantitative and qualitative comparisons.FedFM-Lite can achieve better performance than state-of-the-art methods withfive to ten times less communication costs.

FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learning