Next Article in Journal
Coupled Criticality Analysis of Inflation and Unemployment
Previous Article in Journal
Energy Based Logic Mining Analysis with Hopfield Neural Network for Recruitment Evaluation

Probabilistic Predictions with Federated Learning

Dr. Ing. h.c. F. Porsche AG, 71287 Weissach, Germany
Institute of Vehicle System Technology, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
Author to whom correspondence should be addressed.
Entropy 2021, 23(1), 41;
Received: 20 November 2020 / Revised: 20 December 2020 / Accepted: 26 December 2020 / Published: 30 December 2020
(This article belongs to the Section Information Theory, Probability and Statistics)
Probabilistic predictions with machine learning are important in many applications. These are commonly done with Bayesian learning algorithms. However, Bayesian learning methods are computationally expensive in comparison with non-Bayesian methods. Furthermore, the data used to train these algorithms are often distributed over a large group of end devices. Federated learning can be applied in this setting in a communication-efficient and privacy-preserving manner but does not include predictive uncertainty. To represent predictive uncertainty in federated learning, our suggestion is to introduce uncertainty in the aggregation step of the algorithm by treating the set of local weights as a posterior distribution for the weights of the global model. We compare our approach to state-of-the-art Bayesian and non-Bayesian probabilistic learning algorithms. By applying proper scoring rules to evaluate the predictive distributions, we show that our approach can achieve similar performance as the benchmark would achieve in a non-distributed setting. View Full-Text
Keywords: probabilistic machine learning; federated learning; Bayesian deep learning; predictive uncertainty probabilistic machine learning; federated learning; Bayesian deep learning; predictive uncertainty
Show Figures

Figure 1

MDPI and ACS Style

Thorgeirsson, A.T.; Gauterin, F. Probabilistic Predictions with Federated Learning. Entropy 2021, 23, 41.

AMA Style

Thorgeirsson AT, Gauterin F. Probabilistic Predictions with Federated Learning. Entropy. 2021; 23(1):41.

Chicago/Turabian Style

Thorgeirsson, Adam T., and Frank Gauterin. 2021. "Probabilistic Predictions with Federated Learning" Entropy 23, no. 1: 41.

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

Back to TopTop