Comparative Analysis of Structural Causal Model Fine-Tuning and Data Augmentation on TabBench 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 integration of Structural Causal Models (SCMs) in fine-tuning compare to traditional data augmentation techniques in terms of downstream performance on the TabBench suite under distributional shift?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.4/10.