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/

Zendy Plus

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

Zendy Tools

Zendy Open

Federated learning (FL) allows multiple clients to collaboratively train adeep learning model. One major challenge of FL is when data distribution isheterogeneous, i.e., differs from one client to another. Existing personalizedFL algorithms are only applicable to narrow cases, e.g., one or two dataclasses per client, and therefore they do not satisfactorily address FL undervarying levels of data heterogeneity. In this paper, we propose a novelframework, called DisTrans, to improve FL performance (i.e., model accuracy)via train and test-time distributional transformations along with adouble-input-channel model structure. DisTrans works by optimizingdistributional offsets and models for each FL client to shift their datadistribution, and aggregates these offsets at the FL server to further improveperformance in case of distributional heterogeneity. Our evaluation on multiplebenchmark datasets shows that DisTrans outperforms state-of-the-art FL methodsand data augmentation methods under various settings and different degrees ofclient distributional heterogeneity.

Addressing Heterogeneity in Federated Learning via Distributional Transformation