Differentially private Bayesian learning on distributed data

Many applications of machine learning, for example in health care, would benefit from methods that can guarantee privacy of data subjects. Differential privacy (DP) has become established as a standard for protecting learning results. The standard DP algorithms require a single trusted party to have access to the entire data, which is a clear weakness, or add prohibitive amounts of noise. We consider DP Bayesian learning in a distributed setting, where each party only holds a single sample or a few samples of the data. We propose a learning strategy based on a secure multi-party sum function for aggregating summaries from data holders and the Gaussian mechanism for DP. Our method builds on an asymptotically optimal and practically efficient DP Bayesian inference with rapidly diminishing extra cost.

Authors

• Mikko Heikkilä University of Helsinki
• Eemil Lagerspetz University of Helsinki
• Samuel Kaski Aalto University The University of Manchester
• Kana Shimizu Waseda University
• Sasu Tarkoma
• Antti Honkela

Keywords

No keywords are indexed for this paper.