15 Facts About Federated learning

Federated learning is a machine learning technique that trains an algorithm across multiple decentralized edge devices or servers holding local data samples, without exchanging them.

Federated learning enables multiple actors to build a common, robust machine learning model without sharing data, thus allowing to address critical issues such as data privacy, data security, data access rights and access to heterogeneous data.

Federated learning aims at training a machine learning algorithm, for instance deep neural networks, on multiple local datasets contained in local nodes without explicitly exchanging data samples.

Recently, a new federated learning framework named HeteroFL was developed to address heterogeneous clients equipped with very different computation and communication capabilities.

Recent federated learning developments introduced novel techniques to tackle asynchronicity during the training process, or training with dynamically varying models.

Federated learning requires frequent communication between nodes during the learning process.

Federated learning averaging is a generalization of FedSGD, which allows local nodes to perform more than one batch update on local data and exchanges the updated weights rather than the gradients.

Federated learning methods suffer when the device datasets are heterogeneously distributed.

Meta learning can be incorporated in personalizing federated learning methods to the edge users.

In such cases federated learning brings solutions to train a global model while respecting security constraints.

Federated learning has started to emerge as an important research topic in 2015 and 2016, with the first publications on federated averaging in telecommunication settings.

Federated learning can represent a solution for limiting volume of data transfer and accelerating learning processes.

Federated learning seeks to address the problem of data governance and privacy by training algorithms collaboratively without exchanging the data itself.

Nature Digital Medicine published the paper "The Future of Digital Health with Federated Learning" in September 2020, in which the authors explore how federated learning may provide a solution for the future of digital health, and highlight the challenges and considerations that need to be addressed.

Furthermore, in a published paper "A Systematic Review of Federated Learning in the Healthcare Area: From the Perspective of Data Properties and Applications", the authors trying to provide a set of challenges on FL challenges on medical data-centric perspective.