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

Personalized federated learning (pFL) enables collaborative training amongmultiple clients to enhance the capability of customized local models. In pFL,clients may have heterogeneous (also known as non-IID) data, which poses a keychallenge in how to decouple the data knowledge into generic knowledge forglobal sharing and personalized knowledge for preserving local personalization.A typical way of pFL focuses on label distribution skew, and they adopt adecoupling scheme where the model is split into a common feature extractor andtwo prediction heads (generic and personalized). However, such a decouplingscheme cannot solve the essential problem of feature skew heterogeneity,because a common feature extractor cannot decouple the generic and personalizedfeatures. Therefore, in this paper, we rethink the architecture decouplingdesign for feature-skew pFL and propose an effective pFL method called FediOS.In FediOS, we reformulate the decoupling into two feature extractors (genericand personalized) and one shared prediction head. Orthogonal projections areused for clients to map the generic features into one common subspace andscatter the personalized features into different subspaces to achievedecoupling for them. In addition, a shared prediction head is trained tobalance the importance of generic and personalized features during inference.Extensive experiments on four vision datasets demonstrate our method reachesstate-of-the-art pFL performances under feature skew heterogeneity.

FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learning