Models can be trained jointly without data leaving the device, but it was only validated in simulation

Some data is scattered across a large number of phones, and privacy does not allow it to be centralized on a server. The approach in the FedAvg paper is: each phone trains locally for a few rounds on its own data, and only the model changes are sent up to be averaged, without transmitting raw data, and the number of communication round trips is ten to a hundred times fewer than centralized training. This type of approach is collectively called federated learning.

Today, when vendors advertise that "the model can be improved without uploading data," what runs underneath is still this local training plus averaging, and later improvements are patches on top of it. When you hear this kind of advertising, first ask whether the results were measured in simulation or on real phones; the original paper itself only went as far as simulation.

If devices go offline, if data changes, or if someone deliberately submits bad updates, it handles none of these. If the question is whether this kind of training leaks privacy, or how well it works on real devices, it was only validated in simulation, so don't use it to draw conclusions.

Communication-Efficient Learning of Deep Networks from Decentralized Data (2016) | Next review 2027-09-20