FLAT Encoder Scalability in Large Heterogeneous Tabular Datasets

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 scalable is the FLAT encoder architecture when applied to larger tabular datasets with heterogeneous feature spaces, as measured by F1-score and computational throughput on benchmark datasets like OpenML?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.5/10.