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

Personalized Federated Learning (PFL) represents a promising solution fordecentralized learning in heterogeneous data environments. Partial modelpersonalization has been proposed to improve the efficiency of PFL byselectively updating local model parameters instead of aggregating all of them.However, previous work on partial model personalization has mainly focused onConvolutional Neural Networks (CNNs), leaving a gap in understanding how it canbe applied to other popular models such as Vision Transformers (ViTs). In thiswork, we investigate where and how to partially personalize a ViT model.Specifically, we empirically evaluate the sensitivity to data distribution ofeach type of layer. Based on the insights that the self-attention layer and theclassification head are the most sensitive parts of a ViT, we propose a novelapproach called FedPerfix, which leverages plugins to transfer information fromthe aggregated model to the local client as a personalization. Finally, weevaluate the proposed approach on CIFAR-100, OrganAMNIST, and Office-Homedatasets and demonstrate its effectiveness in improving the model's performancecompared to several advanced PFL methods.

FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning