Privacy-preserving federated machine learning

Abstract

A method preserving privacy in federated machine learning system is provided. In the method, a first computing entity in the federated learning system determines a first labeling matrix based on applying a first set of labeling functions to first data points. The first labeling matrix includes a plurality of first labels. The first computing entity obtains a similarity matrix indicating similarity scores between the first data points and second data points associated with a second computing entity. The first computing entity augments the first labeling matrix by transferring labels from a second labeling matrix into the first labeling matrix using the similarity scores between the first data points and the second data points. The first computing entity trains a discriminative machine learning model associated with the first computing entity based on the first augmented labeling matrix.