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

Though successful, federated learning presents new challenges for machinelearning, especially when the issue of data heterogeneity, also known asNon-IID data, arises. To cope with the statistical heterogeneity, previousworks incorporated a proximal term in local optimization or modified the modelaggregation scheme at the server side or advocated clustered federated learningapproaches where the central server groups agent population into clusters withjointly trainable data distributions to take the advantage of a certain levelof personalization. While effective, they lack a deep elaboration on what kindof data heterogeneity and how the data heterogeneity impacts the accuracyperformance of the participating clients. In contrast to many of the priorfederated learning approaches, we demonstrate not only the issue of dataheterogeneity in current setups is not necessarily a problem but also in factit can be beneficial for the FL participants. Our observations are intuitive:(1) Dissimilar labels of clients (label skew) are not necessarily considereddata heterogeneity, and (2) the principal angle between the agents' datasubspaces spanned by their corresponding principal vectors of data is a betterestimate of the data heterogeneity. Our code is available athttps://github.com/MMorafah/FL-SC-NIID.

Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks