What is Federated Learning?

Federated learning is a distributed machine learning approach that enables organizations to collaborate on machine learning projects without sharing sensitive data, such as, patient records, financial data, or classified secrets (McMahan, 2016; Sheller, Bakas et al., 2020; Yang, Liu, Chen, & Tong, 2019). The basic premise behind federated learning is that the model moves to meet the data rather than the data moving to meet the model. Therefore, the minimum data movement needed across the federation is solely the model parameters and their updates.

Federated Learning