Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

On the byzantine robustness of clustered federated learning

: Sattler, F.; Müller, K.-R.; Wiegand, T.; Samek, W.


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society; IEEE Signal Processing Society:
IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020. Proceedings : May 4-8, 2020, Barcelona, Spain
Piscataway, NJ: IEEE, 2020
ISBN: 978-1-5090-6631-5
ISBN: 978-1-5090-6632-2
International Conference on Acoustics, Speech and Signal Processing (ICASSP) <45, 2020, Barcelona>
Fraunhofer HHI ()

Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it's popularity, it has been observed that Federated Learning yields suboptimal results if the local clients' data distributions diverge. The recently proposed Clustered Federated Learning Framework addresses this issue, by separating the client population into different groups based on the pairwise cosine similarities between their parameter updates. In this work we investigate the application of CFL to byzantine settings, where a subset of clients behaves unpredictably or tries to disturb the joint training effort in an directed or undirected way. We perform experiments with deep neural networks on common Federated Learning datasets which demonstrate that CFL (without modifications) is able to reliably detect byzantine clients and remove them from training.