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

Artificial neural network has achieved unprecedented success in a widevariety of domains such as classifying, predicting and recognizing objects.This success depends on the availability of big data since the training processrequires massive and representative data sets. However, data collection isoften prevented by privacy concerns and people want to take control over theirsensitive information during both training and using processes. To address thisproblem, we propose a privacy-preserving method for the distributed system,Stochastic Channel-Based Federated Learning (SCBF), which enables theparticipants to train a high-performance model cooperatively without sharingtheir inputs. We design, implement and evaluate a channel-based updatealgorithm for the central server in a distributed system, which selects thechannels with regard to the most active features in a training loop and uploadsthem as learned information from local datasets. A pruning process is appliedto the algorithm based on the validation set, which serves as a modelaccelerator. In the experiment, our model presents equal performances andhigher saturating speed than the Federated Averaging method which reveals allthe parameters of local models to the server when updating. We also demonstratethat the converging rates could be increased by introducing a pruning process.

Privacy Preserving Stochastic Channel-Based Federated Learning with Neural Network Pruning