CURATE: Scaling-Up Differentially Private Causal Graph Discovery

Causal graph discovery (CGD) is the process of estimating the underlying probabilistic graphical model that represents the joint distribution of features of a dataset. CGD algorithms are broadly classified into two categories: (i) constraint-based algorithms, where the outcome depends on conditional...

Full description

Saved in:
Bibliographic Details
Published in:Entropy (Basel, Switzerland) Vol. 26; no. 11; p. 946
Main Authors: Bhattacharjee, Payel, Tandon, Ravi
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 05.11.2024
MDPI
Subjects:
Adaptive algorithms
adaptive privacy budgeting
Algorithms
Analysis
Budgeting
Budgets
causal graph discovery
Constraints
Datasets
differential privacy
Estimation
Leakage
Noise prediction
Optimization
Optimization techniques
Privacy
Probability distribution
Random variables
Statistical analysis
New York
United States
Germany
adaptive privacy budgeting
causal graph discovery
differential privacy
ISSN:1099-4300, 1099-4300
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Causal graph discovery (CGD) is the process of estimating the underlying probabilistic graphical model that represents the joint distribution of features of a dataset. CGD algorithms are broadly classified into two categories: (i) constraint-based algorithms, where the outcome depends on conditional independence (CI) tests, and (ii) score-based algorithms, where the outcome depends on optimized score function. Because sensitive features of observational data are prone to privacy leakage, differential privacy (DP) has been adopted to ensure user privacy in CGD. Adding the same amount of noise in this sequential-type estimation process affects the predictive performance of algorithms. Initial CI tests in constraint-based algorithms and later iterations of the optimization process of score-based algorithms are crucial; thus, they need to be more accurate and less noisy. Based on this key observation, we present CURATE (CaUsal gRaph AdapTivE privacy), a DP-CGD framework with adaptive privacy budgeting. In contrast to existing DP-CGD algorithms with uniform privacy budgeting across all iterations, CURATE allows for adaptive privacy budgeting by minimizing error probability (constraint-based), maximizing iterations of the optimization problem (score-based) while keeping the cumulative leakage bounded. To validate our framework, we present a comprehensive set of experiments on several datasets and show that CURATE achieves higher utility compared to existing DP-CGD algorithms with less privacy leakage.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
This paper is an extended version of our published paper: Bhattacharjee, P.; Tandon, R. Adaptive Privacy for Differentially Private Causal Graph Discovery. In Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 2024, London, UK, 22–25 September 2024.
ISSN:1099-4300
1099-4300
DOI:10.3390/e26110946