Federated Learning seems to have a lot of potential, I understand it can be done using different techniques, e.g. functional encryption, etc. The simplest seems to be zero-sum masks. For TensorFlow this is e.g. described here and here.
I've tried to find an example of what this looks like, but there isn't much online, there is a short discussion on this SE, but it wasn't very illuminating. There is maybe something on this Chegg, but paywall.
Would anyone have an MWE of doing aggregation using zero-sum masks?