Scaling Synthetic Datasets in CausalMixFT for Tabular Foundation Model Performance on TabMWP

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: What is the impact of scaling the size of the synthetic dataset generated by CausalMixFT on the fine-tuning performance of tabular foundation models, measured by validation accuracy and downstream task generalization on TabMWP?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.5/10.