Bristle: Decentralized Federated Learning in Byzantine, Non-i.i.d. Environments

no code implementations • 21 Oct 2021 • Joost Verbraeken, Martijn de Vos, Johan Pouwelse

We show that when the training classes are non-i. i. d., Bristle significantly outperforms the accuracy of the most Byzantine-resilient baselines by 2. 3x while reducing communication costs by 90%.

Federated Learning Transfer Learning

A Survey on Distributed Machine Learning

no code implementations • 20 Dec 2019 • Joost Verbraeken, Matthijs Wolting, Jonathan Katzy, Jeroen Kloppenburg, Tim Verbelen, Jan S. Rellermeyer

The demand for artificial intelligence has grown significantly over the last decade and this growth has been fueled by advances in machine learning techniques and the ability to leverage hardware acceleration.

BIG-bench Machine Learning