analiza aiqbench
TabGift introduces a novel approach to tabular data generation by leveraging foundation models with in-context learning, specifically addressing the challenge of synthesizing realistic samples from scarce observations. By mapping heterogeneous tables into a shared latent space and utilizing an in-context diffusion model, it achieves efficient distribution inference that outperforms baselines in low-data regimes. This research advances the field of machine learning by demonstrating how generative priors can be effectively transferred across datasets without requiring large context sets.
TabGift: A Context-Efficient Foundation Model for Tabular Data Generation
arXiv:2610.16990v1 Announce Type: cross Abstract: Tabular data generation aims to synthesize realistic samples from limited observations while faithfully capturing the underlying data distribution. Tabular foundation models (TFMs), pretrained on diverse tabular tasks and adapted through in-context learning, have demonstrated strong predictive capabilities, suggesting the potential of extending this paradigm to tabular data generation. However, the strong predictive performance of TFMs often relies on sufficiently large context sets, whereas tabular generation is typically needed precisely when target data are scarce. Extending the foundation-model paradigm to generation therefore requires reliable distribution inference from only a limited context. To this end, we propose TabGift, a context-efficient tabular foundation model enabling both efficient distribution modeling and effective generation from only a few context samples. TabGift maps heterogeneous tables into a shared latent space with a pretrained tabular encoder, where an in-context diffusion model learns to denoise latent samples conditioned on a small set of clean examples. This design transfers generative priors across datasets and enables distribution inference from limited context, while a lightweight dataset-specific MLP decoder maps generated representations back to the original data space. Experiments on 7 classification and 11 regression datasets show that TabGift consistently outperforms representative baselines in synthetic data quality, with particularly strong gains under limited-context settings, while achieving substantially faster adaptation and generation.
Abstract:Tabular data generation aims to synthesize realistic samples from limited observations while faithfully capturing the underlying data distribution. Tabular foundation models (TFMs), pretrained on diverse tabular tasks and adapted through in-context learning, have demonstrated strong predictive capabilities, suggesting the potential of extending this paradigm to tabular data generation. However, the strong predictive performance of TFMs often relies on sufficiently large context sets, whereas tabular generation is typically needed precisely when target data are scarce. Extending the foundation-model paradigm to generation therefore requires reliable distribution inference from only a limited context. To this end, we propose TabGift, a context-efficient tabular foundation model enabling both efficient distribution modeling and effective generation from only a few context samples. TabGift maps heterogeneous tables into a shared latent space with a pretrained tabular encoder, where an in-context diffusion model learns to denoise latent samples conditioned on a small set of clean examples. This design transfers generative priors across datasets and enables distribution inference from limited context, while a lightweight dataset-specific MLP decoder maps generated representations back to the original data space. Experiments on 7 classification and 11 regression datasets show that TabGift consistently outperforms representative baselines in synthetic data quality, with particularly strong gains under limited-context settings, while achieving substantially faster adaptation and generation.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2610.16990 [cs.LG]
(or arXiv:2610.16990v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.16990 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 306 cuvinte
Subiecte conexe
Introducing TabFM: A zero-shot foundation model for tabular data
Google Research · 30 iun. 2026
NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction
Hugging Face · 29 sept. 2026
Xiaomi-TabLDM: A Tabular Foundation Model Technical Report
arXiv · 5 sept. 2026
Benchmarking Attention for Tabular Foundation Models
arXiv · 28 sept. 2026