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) is an evolving machine learning method in whichmultiple clients participate in collaborative learning without sharing theirdata with each other and the central server. In real-world applications such ashospitals and industries, FL counters the challenges of data heterogeneity andmodel heterogeneity as an inevitable part of the collaborative training. Morespecifically, different organizations, such as hospitals, have their ownprivate data and customized models for local training. To the best of ourknowledge, the existing methods do not effectively address both problems ofmodel heterogeneity and data heterogeneity in FL. In this paper, we exploit thedata and model heterogeneity simultaneously, and propose a method, MDH-FL(Exploiting Model and Data Heterogeneity in FL) to solve such problems toenhance the efficiency of the global model in FL. We use knowledge distillationand a symmetric loss to minimize the heterogeneity and its impact on the modelperformance. Knowledge distillation is used to solve the problem of modelheterogeneity, and symmetric loss tackles with the data and labelheterogeneity. We evaluate our method on the medical datasets to conform thereal-world scenario of hospitals, and compare with the existing methods. Theexperimental results demonstrate the superiority of the proposed approach overthe other existing methods.

Federated Learning for Data and Model Heterogeneity in Medical Imaging