Probabilistic causal graphs as categorical data synthesizers: Do they do better than Gaussian Copulas and Conditional Tabular GANs?

2025-04-15

AI Summary

This study addresses the need for privacy-preserving synthetic data generation for sensitive survey data—such as accessibility to disability services—where preserving causal relationships is critical. We propose a novel method for synthesizing categorical data based on probabilistic causal graphs, which integrate structural equation models with Bayesian networks. Unlike baseline approaches—including Gaussian Copula and CTGAN—that model only statistical associations, our method is the first to systematically incorporate causal graphs into categorical synthetic data generation, explicitly encoding and preserving causal dependencies among variables while maintaining fidelity to marginal distributions. Empirical evaluation demonstrates that our approach significantly outperforms baselines across three key metrics: chi-square test statistics, KL divergence, and total variation distance (TVD), with the most substantial improvement observed in TVD. These results confirm its dual advantages in statistical fidelity and relational validity.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

This study investigates the generation of high-quality synthetic categorical data, such as survey data, using causal graph models. Generating synthetic data aims not only to create a variety of data for training the models but also to preserve privacy while capturing relationships between the data. The research employs Structural Equation Modeling (SEM) followed by Bayesian Networks (BN). We used the categorical data that are based on the survey of accessibility to services for people with disabilities. We created both SEM and BN models to represent causal relationships and to capture joint distributions between variables. In our case studies, such variables include, in particular, demographics, types of disability, types of accessibility barriers and frequencies of encountering those barriers. The study compared the SEM-based BN method with alternative approaches, including the probabilistic Gaussian copula technique and generative models like the Conditional Tabular Generative Adversarial Network (CTGAN). The proposed method outperformed others in statistical metrics, including the Chi-square test, Kullback-Leibler divergence, and Total Variation Distance (TVD). In particular, the BN model demonstrated superior performance, achieving the highest TVD, indicating alignment with the original data. The Gaussian Copula ranked second, while CTGAN exhibited moderate performance. These analyses confirmed the ability of the SEM-based BN to produce synthetic data that maintain statistical and relational validity while maintaining confidentiality. This approach is particularly beneficial for research on sensitive data, such as accessibility and disability studies.

Problem

• Generating high-quality synthetic categorical survey data
• Preserving privacy while capturing data relationships
• Comparing causal graph models with Copulas and CTGANs

Innovation

• Uses Structural Equation Modeling for causal relationships
• Employs Bayesian Networks for joint distributions
• Outperforms Gaussian Copula and CTGAN statistically