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

Latest federated learning (FL) methods started to focus on how to useunlabeled data in clients for training due to users' privacy concerns, highlabeling costs, or lack of expertise. However, current FederatedSemi-Supervised/Self-Supervised Learning (FSSL) approaches fail to learnlarge-scale images because of the limited computing resources of local clients.In this paper, we introduce a new framework FedMAE, which stands for FederatedMasked AutoEncoder, to address the problem of how to utilize unlabeledlarge-scale images for FL. Specifically, FedMAE can pre-train one-block MaskedAutoEncoder (MAE) using large images in lightweight client devices, and thencascades multiple pre-trained one-block MAEs in the server to build amulti-block ViT backbone for downstream tasks. Theoretical analysis andexperimental results on image reconstruction and classification show that ourFedMAE achieves superior performance compared to the state-of-the-art FSSLmethods.

FedMAE: Federated Self-Supervised Learning with One-Block Masked Auto-Encoder