Scaling Synthetic Data Diversity in Tabular Foundation Model Pretraining and Accuracy Degradation under Distributional Shift

Fine-tuning tabular foundation models (TFMs) under data scarcity is challenging, as early stopping on even scarcer validation data often fails to capture true generalization performance. We propose CausalMixFT, a method that enhances fine-tuning robustness and downstream performance by generating structurally consistent synthetic samples using Structural Causal Models (SCMs) fitted on the target dataset. This approach augments limited real data with causally informed synthetic examples, preserving feature dependencies while expanding training diversity. Evaluated across 33 classification datas

Research goal: How does the scaling of synthetic data diversity in tabular foundation model pretraining affect accuracy degradation under distributional shift on the TabBench suite?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.3/10.