Federated Learning via Synthetic Data

TL;DR

This paper introduces a federated learning approach that replaces transmitting model updates with synthetic data, significantly reducing communication costs while maintaining model performance.

Contribution

It proposes a novel method for federated learning that transmits synthetic data instead of model updates, reducing communication overhead.

Findings

Over an order of magnitude reduction in communication costs

Minimal degradation in model accuracy

Potential for scalable federated learning applications

Abstract

Federated learning allows for the training of a model using data on multiple clients without the clients transmitting that raw data. However the standard method is to transmit model parameters (or updates), which for modern neural networks can be on the scale of millions of parameters, inflicting significant computational costs on the clients. We propose a method for federated learning where instead of transmitting a gradient update back to the server, we instead transmit a small amount of synthetic `data'. We describe the procedure and show some experimental results suggesting this procedure has potential, providing more than an order of magnitude reduction in communication costs with minimal model degradation.