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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Federated learning is a distributed machine learning approach in whichclients train models locally with their own data and upload them to a server sothat their trained results are shared between them without uploading raw datato the server. There are some challenges in federated learning, such ascommunication size reduction and client heterogeneity. The former can mitigatethe communication overheads, and the latter can allow the clients to chooseproper models depending on their available compute resources. To address thesechallenges, in this paper, we utilize Neural ODE based models for federatedlearning. The proposed flexible federated learning approach can reduce thecommunication size while aggregating models with different iteration counts ordepths. Our contribution is that we experimentally demonstrate that theproposed federated learning can aggregate models with different iterationcounts or depths. It is compared with a different federated learning approachin terms of the accuracy. Furthermore, we show that our approach can reducecommunication size by up to 92.4% compared with a baseline ResNet model usingCIFAR-10 dataset.

Federated Learning of Neural ODE Models with Different Iteration Counts