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) has been proved to be an effective learning frameworkwhen data cannot be centralized due to privacy, communication costs, andregulatory restrictions. When training deep learning models under an FLsetting, people employ the predefined model architecture discovered in thecentralized environment. However, this predefined architecture may not be theoptimal choice because it may not fit data with non-identical and independentdistribution (non-IID). Thus, we advocate automating federated learning(AutoFL) to improve model accuracy and reduce the manual design effort. Wespecifically study AutoFL via Neural Architecture Search (NAS), which canautomate the design process. We propose a Federated NAS (FedNAS) algorithm tohelp scattered workers collaboratively searching for a better architecture withhigher accuracy. We also build a system based on FedNAS. Our experiments onnon-IID dataset show that the architecture searched by FedNAS can outperformthe manually predefined architecture.

Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Search