Improving Generalization Accuracy with SCM-based Synthetic Data for Tabular Foundation Models

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: Does fine-tuning tabular foundation models with Structural Causal Model-based synthetic data improve generalization accuracy more than standard data augmentation when validation sets are scarce?

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