SCM-based synthetic augmentation for reducing validation data requirements in fine-tuning stability

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: Can SCM-based synthetic augmentation reduce the validation data requirements for early stopping in fine-tuning, as measured by the stability of accuracy across multiple validation splits on the Tabular Playground Series datasets?

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