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

Model compression is important in federated learning (FL) with large modelsto reduce communication cost. Prior works have been focusing on sparsificationbased compression that could desparately affect the global model accuracy. Inthis work, we propose a new scheme for upstream communication where instead oftransmitting the model update, each client learns and transmits a light-weightsynthetic dataset such that using it as the training data, the model performssimilarly well on the real training data. The server will recover the localmodel update via the synthetic data and apply standard aggregation. We thenprovide a new algorithm FedSynth to learn the synthetic data locally.Empirically, we find our method is comparable/better than random maskingbaselines in all three common federated learning benchmark datasets.

FedSynth: Gradient Compression via Synthetic Data in Federated Learning