A privacy-preserving algorithm for distributed training of neural network ensembles

24 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Distributed learning of deep neural network over multiple agents (2018, methodology): “Some interesting solutions include using Ada-boost to jointly train classiﬁer ensembles [28], using random rotation perturbations for homomorphic pseudo-encryption [29] and applying homomorphic cryptosystem to perform secure computation [30].”
A Framework for Parallel and Distributed Training of Neural Networks (2016, background): “Most authors resort either to an ensemble of models trained independently by the agents (Lazarevic and Obradovic, 2002; Zhang and Zhong, 2013), or to strategies requiring the sum of the gradients’ contributions for all agents at every single iteration (Samet and Miri, 2012; Georgopoulos and Hasler,…”