Differentially Private Learning of Undirected Graphical Models using Collective Graphical Models

by   Garrett Bernstein, et al.

We investigate the problem of learning discrete, undirected graphical models in a differentially private way. We show that the approach of releasing noisy sufficient statistics using the Laplace mechanism achieves a good trade-off between privacy, utility, and practicality. A naive learning algorithm that uses the noisy sufficient statistics "as is" outperforms general-purpose differentially private learning algorithms. However, it has three limitations: it ignores knowledge about the data generating process, rests on uncertain theoretical foundations, and exhibits certain pathologies. We develop a more principled approach that applies the formalism of collective graphical models to perform inference over the true sufficient statistics within an expectation-maximization framework. We show that this learns better models than competing approaches on both synthetic data and on real human mobility data used as a case study.


page 1

page 2

page 3

page 4


Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models

Directed graphical models (DGMs) are a class of probabilistic models tha...

Relaxed Marginal Consistency for Differentially Private Query Answering

Many differentially private algorithms for answering database queries in...

Two Differentially Private Rating Collection Mechanisms for Recommender Systems

We design two mechanisms for the recommender system to collect user rati...

Oneshot Differentially Private Top-k Selection

Being able to efficiently and accurately select the top-k elements witho...

A Knowledge Transfer Framework for Differentially Private Sparse Learning

We study the problem of estimating high dimensional models with underlyi...

Asymptotic theory in a class of directed random graph models with a differentially private bi-degree sequence

Although the asymptotic properties of the parameter estimator have been ...

Characterization of differentially expressed genes using high-dimensional co-expression networks

We present a technique to characterize differentially expressed genes in...