paper-with-me

Papers

Exploring Fine-Tuning for Tabular Foundation Models

2026-01-14 · Aditya Tanna, Pratinav Seth, Mohamed Bouadi, Vinay Kumar Sankarapu arxiv

Tabular Foundation Models (TFMs) have recently shown strong in-context learning capabilities on structured data, achieving zero-shot performance comparable to traditional machine learning methods. We find that zero-shot TFMs already achieve strong performance, while the benefits of fine-tuning are highly model and data-dependent. Meta-learning and PEFT provide moderate gains under specific conditions, whereas full supervised fine-tuning (SFT) often reduces accuracy or calibration quality. This work presents the first comprehensive study of fine-tuning in TFMs across benchmarks including TALENT, OpenML-CC18, and TabZilla. We compare Zero-Shot, Meta-Learning, Supervised (SFT), and parameter-efficient (PEFT) approaches, analyzing how dataset factors such as imbalance, size, and dimensionality affect outcomes. Our findings cover performance, calibration, and fairness, offering practical guidelines on when fine-tuning is most beneficial and its limitations.

📄 PDF Abstract BibTeX arXiv:2601.09654

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection

2024-08-06 · Yuxin Wang, Duanyu Feng, Yongfu Dai, Zhengyu Chen 외

Data serves as the fundamental foundation for advancing deep learning, particularly tabular data presented in a structured format, which is highly conducive to modeling. However, even in the era of LLM, obtaining tabular…

Privacy PreservingSynthetic Data GenerationTabular Data Generation

TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models

2025-11-04 · Aditya Tanna, Pratinav Seth, Mohamed Bouadi, Utsav Avaiya 외 arxiv

Tabular foundation models represent a growing paradigm in structured data learning, extending the benefits of large-scale pretraining to tabular domains. However, their adoption remains limited due to heterogeneous prepr…

parameter-efficient fine-tuning

TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models

2026-05-07 · Duong Nguyen, Mohammed Jawhar, Nicolas Chesneau arxiv

Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance through in-context learning, but their inductive biases remain fixed at inference…

Binary Classification

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

2026-01-07 · Magnus Bühler, Lennart Purucker, Frank Hutter arxiv

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 …

Data Augmentation

KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models

2026-06-29 · Boshko Koloski, Xiangjian Jiang, Senja Pollak, Blaž Škrlj 외 arxiv

Tabular foundation models have advanced deep learning for tabular data by delivering strong default performance across many small and medium tasks. Yet in niche domains, where data is scarce, high-dimensional, and shifte…

Knowledge Graphs