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 enables many local devices to train a deep learning modeljointly without sharing the local data. Currently, most of federated trainingschemes learns a global model by averaging the parameters of local models.However, most of these training schemes suffer from high communication costresulted from transmitting full local model parameters. Moreover, directlyaveraging model parameters leads to a significant performance degradation, dueto the class-imbalanced non-iid data on different devices. Especially for thereal life federated learning tasks involving extreme classification, (1)communication becomes the main bottleneck since the model size increasesproportionally to the number of output classes; (2) extreme classification(such as user recommendation) normally have extremely imbalanced classes andheterogeneous data on different devices. To overcome this problem, we proposefederated multiple label hashing (FedMLH), which leverages label hashing tosimultaneously reduce the model size (up to 3.40X decrease) with communicationcost (up to 18.75X decrease) and achieves significant better accuracy (up to35.5%} relative accuracy improvement) and faster convergence rate (up to 5.5Xincrease) for free on the federated extreme classification tasks compared tofederated average algorithm.

Federated Multiple Label Hashing (FedMLH): Communication Efficient Federated Learning on Extreme Classification Tasks