Comparative Analysis of Cross-Domain Generalization in Privacy-Preserving Tabular GANs With and Without Differential Privacy

Generative models have revolutionized multiple domains, yet their application to tabular data remains underexplored. Evaluating generative models for tabular data presents unique challenges due to structural complexity, large-scale variability, and mixed data types, making it difficult to intuitively capture intricate patterns. Existing evaluation metrics offer only partial insights, lacking a comprehensive measure of generative performance. To address this limitation, we propose three novel evaluation metrics: FAED, FPCAD, and RFIS. Our extensive experimental analysis, conducted on three stan

Research goal: How do privacy-preserving tabular GANs trained with DP compare to non-DP versions in cross-domain generalization, measured by transfer learning performance and domain adaptation benchmarks?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.9/10.