The Interpolated MVU Mechanism For Communication-efficient Private Federated Learning. (arXiv:2211.03942v1 [cs.LG])

We consider private federated learning (FL), where a server aggregates
differentially private gradient updates from a large number of clients in order
to train a machine learning model. The main challenge is balancing privacy with
both classification accuracy of the learned model as well as the amount of
communication between the clients and server. In this work, we build on a
recently proposed method for communication-efficient private FL -- the MVU
mechanism -- by introducing a new interpolation mechanism that …

communication federated learning