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

As a promising approach to deal with distributed data, Federated Learning(FL) achieves major advancements in recent years. FL enables collaborativemodel training by exploiting the raw data dispersed in multiple edge devices.However, the data is generally non-independent and identically distributed,i.e., statistical heterogeneity, and the edge devices significantly differ interms of both computation and communication capacity, i.e., systemheterogeneity. The statistical heterogeneity leads to severe accuracydegradation while the system heterogeneity significantly prolongs the trainingprocess. In order to address the heterogeneity issue, we propose anAsynchronous Staleness-aware Model Update FL framework, i.e., FedASMU, with twonovel methods. First, we propose an asynchronous FL system model with adynamical model aggregation method between updated local models and the globalmodel on the server for superior accuracy and high efficiency. Then, we proposean adaptive local model adjustment method by aggregating the fresh global modelwith local models on devices to further improve the accuracy. Extensiveexperimentation with 6 models and 5 public datasets demonstrates that FedASMUsignificantly outperforms baseline approaches in terms of accuracy (0.60% to23.90% higher) and efficiency (3.54% to 97.98% faster).

FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Update