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

Federated learning (FL) enables multiple clients to train modelscollaboratively without sharing local data, which has achieved promisingresults in different areas, including the Internet of Things (IoT). However,end IoT devices do not have abilities to automatically annotate their collecteddata, which leads to the label shortage issue at the client side. Tocollaboratively train an FL model, we can only use a small number of labeleddata stored on the server. This is a new yet practical scenario in federatedlearning, i.e., labels-at-server semi-supervised federated learning (SemiFL).Although several SemiFL approaches have been proposed recently, none of themcan focus on the personalization issue in their model design. IoT environmentsmake SemiFL more challenging, as we need to take device computationalconstraints and communication cost into consideration simultaneously. To tacklethese new challenges together, we propose a novel SemiFL framework namedpFedKnow. pFedKnow generates lightweight personalized client models via neuralnetwork pruning techniques to reduce communication cost. Moreover, itincorporates pretrained large models as prior knowledge to guide theaggregation of personalized client models and further enhance the frameworkperformance. Experiment results on both image and text datasets show that theproposed pFedKnow outperforms state-of-the-art baselines as well as reducingconsiderable communication cost. The source code of the proposed pFedKnow isavailable at https://github.com/JackqqWang/pfedknow/tree/master.

Knowledge-Enhanced Semi-Supervised Federated Learning for Aggregating Heterogeneous Lightweight Clients in IoT