Bayesian Neural Matching for Federated Learning (nm-gibbs)

This is an implementation of neural matching using Gibbs sampler. It is built upon PyIBP, with major modifications. (https://github.com/kzhai/PyIBP)

This implementation purely takes weights of a neural network and performing neural matching. For testing and validation purposes, the framework of the package "Probabilistic Federated Neural Matching" was used. But for copyright reasons, we will not include this part of the code. (https://github.com/IBM/probabilistic-federated-neural-matching)

LICENSE

This software is open-source, released under the terms of the GNU General Public License version 3, or any later version of the GPL (see COPYING).