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 offers a way to train deep neural networks in adistributed fashion. While this addresses limitations related to distributeddata, it incurs a communication overhead as the model parameters or gradientsneed to be exchanged regularly during training. This can be an issue with largescale distribution of learning tasks and negate the benefit of the respectiveresource distribution. In this paper, we we propose to utilise parallelAdapters for Federated Learning. Using various datasets, we show that Adapterscan be incorporated to different Federated Learning techniques. We highlightthat our approach can achieve similar inference performance compared totraining the full model while reducing the communication overhead by roughly90%. We further explore the applicability of Adapters in cross-silo andcross-device settings, as well as different non-IID data distributions.

Adaptive Parameterization of Deep Learning Models for Federated Learning