Fidelity of Synthetic Tabular Samples and Foundation Model Fine-Tuning Performance

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 correlation between the fidelity of synthetic tabular samples generated via SCMs and the downstream fine-tuning performance of foundation models across heterogeneous domain benchmarks?

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