Differentially Private Federated Variational Inference

by   Mrinank Sharma, et al.

In many real-world applications of machine learning, data are distributed across many clients and cannot leave the devices they are stored on. Furthermore, each client's data, computational resources and communication constraints may be very different. This setting is known as federated learning, in which privacy is a key concern. Differential privacy is commonly used to provide mathematical privacy guarantees. This work, to the best of our knowledge, is the first to consider federated, differentially private, Bayesian learning. We build on Partitioned Variational Inference (PVI) which was recently developed to support approximate Bayesian inference in the federated setting. We modify the client-side optimisation of PVI to provide an (ϵ, δ)-DP guarantee. We show that it is possible to learn moderately private logistic regression models in the federated setting that achieve similar performance to models trained non-privately on centralised data.



There are no comments yet.


page 10


Differentially Private Variational Inference for Non-conjugate Models

Many machine learning applications are based on data collected from peop...

Generative Models for Effective ML on Private, Decentralized Datasets

To improve real-world applications of machine learning, experienced mode...

Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation

Computing the noisy sum of real-valued vectors is an important primitive...

Decentralized Differentially Private Segmentation with PATE

When it comes to preserving privacy in medical machine learning, two imp...

Boosting Model Performance through Differentially Private Model Aggregation

A key factor in developing high performing machine learning models is th...

Federated Intrusion Detection for IoT with Heterogeneous Cohort Privacy

Internet of Things (IoT) devices are becoming increasingly popular and a...

Federated and Differentially Private Learning for Electronic Health Records

The use of collaborative and decentralized machine learning techniques s...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.