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 emerged as a new paradigm for training machinelearning models distributively without sacrificing data security and privacy.Learning models on edge devices such as mobile phones is one of the most commonuse cases for FL. However, Non-identical independent distributed~(non-IID) datain edge devices easily leads to training failures. Especially,over-parameterized machine learning models can easily be over-fitted on suchdata, hence, resulting in inefficient federated learning and poor modelperformance. To overcome the over-fitting issue, we proposed an adaptivedynamic pruning approach for FL, which can dynamically slim the model bydropping out unimportant parameters, hence, preventing over-fittings. Since themachine learning model's parameters react differently for different trainingsamples, adaptive dynamic pruning will evaluate the salience of the model'sparameter according to the input training sample, and only retain the salientparameter's gradients when doing back-propagation. We performed comprehensiveexperiments to evaluate our approach. The results show that our approach byremoving the redundant parameters in neural networks can significantly reducethe over-fitting issue and greatly improves the training efficiency. Inparticular, when training the ResNet-32 on CIFAR-10, our approach reduces thecommunication cost by 57\%. We further demonstrate the inference accelerationcapability of the proposed algorithm. Our approach reduces up to 50\% FLOPsinference of DNNs on edge devices while maintaining the model's quality.

Heterogeneous Federated Learning using Dynamic Model Pruning and Adaptive Gradient