Bayesian Federated Learning via Predictive Distribution Distillation. (arXiv:2206.07562v1 [cs.LG])

Web: http://arxiv.org/abs/2206.07562

For most existing federated learning algorithms, each round consists of
minimizing a loss function at each client to learn an optimal model at the
client, followed by aggregating these client models at the server. Point
estimation of the model parameters at the clients does not take into account
the uncertainty in the models estimated at each client. In many situations,
however, especially in limited data settings, it is beneficial to take into
account the uncertainty in the client models for …

arxiv bayesian distillation distribution federated learning learning lg predictive