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

In federated learning, data heterogeneity is a critical challenge. Astraightforward solution is to shuffle the clients' data to homogenize thedistribution. However, this may violate data access rights, and how and whenshuffling can accelerate the convergence of a federated optimization algorithmis not theoretically well understood. In this paper, we establish a precise andquantifiable correspondence between data heterogeneity and parameters in theconvergence rate when a fraction of data is shuffled across clients. We provethat shuffling can quadratically reduce the gradient dissimilarity with respectto the shuffling percentage, accelerating convergence. Inspired by the theory,we propose a practical approach that addresses the data access rights issue byshuffling locally generated synthetic data. The experimental results show thatshuffling synthetic data improves the performance of multiple existingfederated learning algorithms by a large margin.

Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity