Causal Data Augmentation for Robust Fine-Tuning of Tabular Foundation Models

• URL: http://arxiv.org/abs/2601.04110v1
• Date: Wed, 07 Jan 2026 17:16:39 GMT
• Title: Causal Data Augmentation for Robust Fine-Tuning of Tabular Foundation Models
• Authors: Magnus Bühler, Lennart Purucker, Frank Hutter,
• Abstract summary: CausalMixFT is a method that enhances fine-tuning robustness and downstream performance.<n>It generates structurally consistent synthetic samples using Structural Causal Models (SCMs) fitted on the target dataset.<n> evaluated across 33 classification datasets from TabArena and over 2300 fine-tuning runs.
• Score: 45.21399037022976
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 datasets from TabArena and over 2300 fine-tuning runs, our CausalMixFT method consistently improves median normalized ROC-AUC from 0.10 (standard fine-tuning) to 0.12, outperforming purely statistical generators such as CTGAN (-0.01), TabEBM (-0.04), and TableAugment (-0.09). Moreover, it narrows the median validation-test performance correlation gap from 0.67 to 0.30, enabling more reliable validation-based early stopping, a key step toward improving fine-tuning stability under data scarcity. These results demonstrate that incorporating causal structure into data augmentation provides an effective and principled route to fine-tuning tabular foundation models in low-data regimes.

Related papers

• STAR : Bridging Statistical and Agentic Reasoning for Large Model Performance Prediction [78.0692157478247]
  We propose STAR, a framework that bridges data-driven STatistical expectations with knowledge-driven Agentic Reasoning.<n>We show that STAR consistently outperforms all baselines on both score-based and rank-based metrics.
  arXiv  Detail & Related papers  (2026-02-12T16:30:07Z)
• Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN [3.059960033014892]
  We evaluate the Tabular Prior-data Fitted Network (TabPFN) and its fine-tuned variants.<n>Our results reveal that while TabPFN achieves stronger predictive accuracy compared to baselines, improvements in fairness are moderate and inconsistent.<n>These findings suggest that the causal pre-training in TabPFN is helpful but insufficient for algorithmic fairness.
  arXiv  Detail & Related papers  (2026-01-25T17:17:12Z)
• The GT-Score: A Robust Objective Function for Reducing Overfitting in Data-Driven Trading Strategies [51.56484100374058]
  GT-Score is a composite objective function that integrates performance, statistical significance, consistency, and downside risk.<n>In walk-forward validation, GT-Score improves the generalization ratio by 98% relative to baseline objective functions.<n>These results suggest that embedding an anti-overfitting structure into the objective can improve the reliability of backtests in quantitative research.
  arXiv  Detail & Related papers  (2026-01-22T05:16:47Z)
• Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling [105.8570596633629]
  We rethink long-tailed dataset distillation by revisiting the limitations of trajectory-based methods.<n>We adopt the statistical alignment perspective to jointly model bias and restore fair supervision.<n>Our approach improves top-1 accuracy by 15.6% on CIFAR-100-LT and 11.8% on Tiny-ImageNet-LT.
  arXiv  Detail & Related papers  (2025-11-24T07:57:01Z)
• SG-OIF: A Stability-Guided Online Influence Framework for Reliable Vision Data [6.4391040754741296]
  In this paper, we introduce a Stability-Guided Online Influence Framework (SG-OIF) for Approximating training-point influence on test predictions.<n>We show that SG-OIF achieves 91.1% accuracy in the top 1% prediction samples on the CIFAR-10, and 99.8% AUPR score on MNIST.
  arXiv  Detail & Related papers  (2025-11-21T19:58:54Z)
• Estimating Time Series Foundation Model Transferability via In-Context Learning [74.65355820906355]
  Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training.<n>Fine-tuning remains critical for boosting performance in domains with limited public data.<n>We introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem.
  arXiv  Detail & Related papers  (2025-09-28T07:07:13Z)
• TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction [24.266135702821334]
  Non-independent and identically distributed (Non-IID) data across edge clients have long posed significant challenges to federated learning (FL) training.<n>We propose TACO, a novel algorithm that addresses the non-IID nature of clients' data by implementing fine-grained, client-specific gradient correction and model aggregation.<n>To enhance the training efficiency, TACO deploys a lightweight model correction and tailored aggregation approach that requires minimum overhead and no extra information beyond the synchronized model parameters.
  arXiv  Detail & Related papers  (2025-04-24T13:16:21Z)
• Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data [39.40116554523575]
  We present Drift-Resilient TabPFN, a fresh approach based on In-Context Learning with a Prior-Data Fitted Network. It learns to approximate Bayesian inference on synthetic datasets drawn from a prior. It improves accuracy from 0.688 to 0.744 and ROC AUC from 0.786 to 0.832 while maintaining stronger calibration.
  arXiv  Detail & Related papers  (2024-11-15T23:49:23Z)
• AutoFT: Learning an Objective for Robust Fine-Tuning [60.641186718253735]
  Foundation models encode rich representations that can be adapted to downstream tasks by fine-tuning. Current approaches to robust fine-tuning use hand-crafted regularization techniques. We propose AutoFT, a data-driven approach for robust fine-tuning.
  arXiv  Detail & Related papers  (2024-01-18T18:58:49Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification [73.87160347728314]
  We investigate how natural background colors play a role as spurious features by annotating the test sets of CIFAR10 and CIFAR100 into subgroups based on the background color of each image. We find that overall human-level accuracy does not guarantee consistent subgroup performances, and the phenomenon remains even on models pre-trained on ImageNet or after data augmentation (DA) Experimental results show that FlowAug achieves more consistent subgroup results than other types of DA methods on CIFAR10/100 and on CIFAR10/100-C.
  arXiv  Detail & Related papers  (2022-12-16T18:51:10Z)
• Elastic weight consolidation for better bias inoculation [24.12790037712358]
  Elastic weight consolidation (EWC) allows fine-tuning of models to mitigate biases. EWC dominates standard fine-tuning, yielding models with lower levels of forgetting on the original (biased) dataset.
  arXiv  Detail & Related papers  (2020-04-29T17:45:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.