Differentially Private Vertical Federated Learning. (arXiv:2211.06782v1 [cs.LG])

A successful machine learning (ML) algorithm often relies on a large amount
of high-quality data to train well-performed models. Supervised learning
approaches, such as deep learning techniques, generate high-quality ML
functions for real-life applications, however with large costs and human
efforts to label training data. Recent advancements in federated learning (FL)
allow multiple data owners or organisations to collaboratively train a machine
learning model without sharing raw data. In this light, vertical FL allows
organisations to build a global model …

federated learning