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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Federated machine learning is a versatile and flexible tool to utilizedistributed data from different sources, especially when communicationtechnology develops rapidly and an unprecedented amount of data could becollected on mobile devices nowadays. Federated learning method exploits notonly the data but the computational power of all devices in the network toachieve more efficient model training. Nevertheless, while most traditionalfederated learning methods work well for homogeneous data and tasks, adaptingthe method to a different heterogeneous data and task distribution ischallenging. This limitation has constrained the applications of federatedlearning in real-world contexts, especially in healthcare settings. Inspired bythe fundamental idea of meta-learning, in this study we propose a newalgorithm, which is an integration of federated learning and meta-learning, totackle this issue. In addition, owing to the advantage of transfer learning formodel generalization, we further improve our algorithm by introducing partialparameter sharing. We name this method partial meta-federated learning (PMFL).Finally, we apply the algorithms to two medical datasets. We show that ouralgorithm could obtain the fastest training speed and achieve the bestperformance when dealing with heterogeneous medical datasets.

PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records