Federated Learning via Synthetic Data
This addresses the computational burden for clients in federated learning, though it appears incremental as it modifies an existing approach rather than introducing a new paradigm.
The paper tackles the high communication cost in federated learning by proposing a method where clients transmit synthetic data instead of gradient updates, achieving more than an order of magnitude reduction in communication costs with minimal model degradation.
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.