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

Although federated learning has achieved many breakthroughs recently, theheterogeneous nature of the learning environment greatly limits its performanceand hinders its real-world applications. The heterogeneous data, time-varyingwireless conditions and computing-limited devices are three main challenges,which often result in an unstable training process and degraded accuracy.Herein, we propose strategies to address these challenges. Targeting theheterogeneous data distribution, we propose a novel adaptive mixing aggregation(AMA) scheme that mixes the model updates from previous rounds with currentrounds to avoid large model shifts and thus, maintain training stability. Wefurther propose a novel staleness-based weighting scheme for the asynchronousmodel updates caused by the dynamic wireless environment. Lastly, we propose anovel CPU-friendly computation-reduction scheme based on transfer learning bysharing the feature extractor (FES) and letting the computing-limited devicesupdate only the classifier. The simulation results show that the proposedframework outperforms existing state-of-the-art solutions and increases thetest accuracy, and training stability by up to 2.38%, 93.10% respectively.Additionally, the proposed framework can tolerate communication delay of up to15 rounds under a moderate delay environment without significant accuracydegradation.

Distributed Learning in Heterogeneous Environment: federated learning with adaptive aggregation and computation reduction