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) has been promoted as a popular technique for trainingmachine learning (ML) models over edge/fog networks. Traditionalimplementations of FL have largely neglected the potential for inter-networkcooperation, treating edge/fog devices and other infrastructure participatingin ML as separate processing elements. Consequently, FL has been vulnerable toseveral dimensions of network heterogeneity, such as varying computationcapabilities, communication resources, data qualities, and privacy demands. Weadvocate for cooperative federated learning (CFL), a cooperative edge/fog MLparadigm built on device-to-device (D2D) and device-to-server (D2S)interactions. Through D2D and D2S cooperation, CFL counteracts networkheterogeneity in edge/fog networks through enabling a model/data/resourcepooling mechanism, which will yield substantial improvements in ML modeltraining quality and network resource consumption. We propose a set of coremethodologies that form the foundation of D2D and D2S cooperation and presentpreliminary experiments that demonstrate their benefits. We also discuss new FLfunctionalities enabled by this cooperative framework such as the integrationof unlabeled data and heterogeneous device privacy into ML model training.Finally, we describe some open research directions at the intersection ofcooperative edge/fog and FL.

Towards Cooperative Federated Learning over Heterogeneous Edge/Fog Networks