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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Federated Learning (FL) is a decentralized learning paradigm, in whichmultiple clients collaboratively train deep learning models withoutcentralizing their local data, and hence preserve data privacy. Real-worldapplications usually involve a distribution shift across the datasets of thedifferent clients, which hurts the generalization ability of the clients tounseen samples from their respective data distributions. In this work, weaddress the recently proposed feature shift problem where the clients havedifferent feature distributions, while the label distribution is the same. Wepropose Federated Representation Augmentation (FRAug) to tackle this practicaland challenging problem. Our approach generates synthetic client-specificsamples in the embedding space to augment the usually small client datasets.For that, we train a shared generative model to fuse the clients knowledgelearned from their different feature distributions. This generator synthesizesclient-agnostic embeddings, which are then locally transformed intoclient-specific embeddings by Representation Transformation Networks (RTNets).By transferring knowledge across the clients, the generated embeddings act as aregularizer for the client models and reduce overfitting to the local originaldatasets, hence improving generalization. Our empirical evaluation on publicbenchmarks and a real-world medical dataset demonstrates the effectiveness ofthe proposed method, which substantially outperforms the currentstate-of-the-art FL methods for non-IID features, including PartialFed andFedBN.

FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation