Boosting Model Performance through Differentially Private Model Aggregation

11/12/2018
by   Sophia Collet, et al.
0

A key factor in developing high performing machine learning models is the availability of sufficiently large datasets. This work is motivated by applications arising in Software as a Service (SaaS) companies where there exist numerous similar yet disjoint datasets from multiple client companies. To overcome the challenges of insufficient data without explicitly aggregating the clients' datasets due to privacy concerns, one solution is to collect more data for each individual client, another is to privately aggregate information from models trained on each client's data. In this work, two approaches for private model aggregation are proposed that enable the transfer of knowledge from existing models trained on other companies' datasets to a new company with limited labeled data while protecting each client company's underlying individual sensitive information. The two proposed approaches are based on state-of-the-art private learning algorithms: Differentially Private Permutation-based Stochastic Gradient Descent and Approximate Minima Perturbation. We empirically show that by leveraging differentially private techniques, we can enable private model aggregation and augment data utility while providing provable mathematical guarantees on privacy. The proposed methods thus provide significant business value for SaaS companies and their clients, specifically as a solution for the cold-start problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/24/2019

Differentially Private Federated Variational Inference

In many real-world applications of machine learning, data are distribute...
research
04/20/2023

DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase

Differentially private synthetic data is a promising alternative for sen...
research
08/20/2019

AdaCliP: Adaptive Clipping for Private SGD

Privacy preserving machine learning algorithms are crucial for learning ...
research
03/02/2021

DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing

Deep learning techniques have achieved remarkable performance in wide-ra...
research
10/19/2021

FriendlyCore: Practical Differentially Private Aggregation

Differentially private algorithms for common metric aggregation tasks, s...
research
11/24/2019

PAC learning with stable and private predictions

We study binary classification algorithms for which the prediction on an...

Please sign up or login with your details

Forgot password? Click here to reset