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 decentralized machine learning architecture,which leverages a large number of remote devices to learn a joint model withdistributed training data. However, the system-heterogeneity is one majorchallenge in a FL network to achieve robust distributed learning performance,which comes from two aspects: i) device-heterogeneity due to the diversecomputational capacity among devices; ii) data-heterogeneity due to thenon-identically distributed data across the network. Prior studies addressingthe heterogeneous FL issue, e.g., FedProx, lack formalization and it remains anopen problem. This work first formalizes the system-heterogeneous FL problemand proposes a new algorithm, called FedLGA, to address this problem bybridging the divergence of local model updates via gradient approximation. Toachieve this, FedLGA provides an alternated Hessian estimation method, whichonly requires extra linear complexity on the aggregator. Theoretically, we showthat with a device-heterogeneous ratio $\rho$, FedLGA achieves convergencerates on non-i.i.d. distributed FL training data for the non-convexoptimization problems with $\mathcal{O} \left( \frac{(1+\rho)}{\sqrt{ENT}} +\frac{1}{T} \right)$ and $\mathcal{O} \left( \frac{(1+\rho)\sqrt{E}}{\sqrt{TK}}+ \frac{1}{T} \right)$ for full and partial device participation respectively,where $E$ is the number of local learning epoch, $T$ is the number of totalcommunication round, $N$ is the total device number and $K$ is the number ofselected device in one communication round under partially participationscheme. The results of comprehensive experiments on multiple datasets show thatFedLGA outperforms current FL methods against the system-heterogeneity.

FedLGA: Towards System-Heterogeneity of Federated Learning via Local Gradient Approximation