13 citations · 16 across the 4 of their papers we have counts for
3 papers · 1 filter
FedAUXfdp: Differentially Private One-Shot Federated Distillation
Haley Hoech, Roman Rischke, Karsten Müller +1
Federated learning suffers in the case of non-iid local datasets, i.e., when the distributions of the clients' data are heterogeneous. One promising approach to this challenge is t…
FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning
Felix Sattler, Tim Korjakow, Roman Rischke +1
Federated Distillation (FD) is a popular novel algorithmic paradigm for Federated Learning, which achieves training performance competitive to prior parameter averaging based metho…
Communication-Efficient Federated Distillation
Felix Sattler, Arturo Marban, Roman Rischke +1
Communication constraints are one of the major challenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmi…