Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

Hugging Face Daily Papers Papers

Summary

Proposes TAP, a tabular augmentation policy that couples diffusion inpainting with a learner-conditioned policy to improve downstream model performance under data scarcity, outperforming strong baselines on real-world datasets.

Generative tabular augmentation is appealing in data-scarce domains, yet the prevailing focus on distributional fidelity does not reliably translate into better downstream models. We formalize a fidelity-utility gap: common generative objectives prioritize distributional plausibility, whereas augmentation succeeds only when injected samples reduce the current learner's held-out evaluation loss. This gap motivates learning not just how to generate, but what to generate and when to inject as training evolves. We propose TAP (Tabular Augmentation Policy), which couples diffusion inpainting with a lightweight, learner-conditioned policy to steer generation toward high-utility regions and controls safe injection via explicit gating and conservative windowed commitment. Under severe data scarcity, TAP consistently outperforms strong generative baselines on seven real-world datasets, improving classification accuracy by up to 15.6 percentage points and reducing regression RMSE by up to 32%.
Original Article
View Cached Full Text

Cached at: 05/14/26, 08:20 PM

Paper page - Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

Source: https://huggingface.co/papers/2605.10315

Abstract

Tabular augmentation policy combines diffusion inpainting with a learner-conditioned policy to improve downstream model performance under data scarcity.

Generative tabular augmentationis appealing indata-scarce domains, yet the prevailing focus ondistributional fidelitydoes not reliably translate into better downstream models. We formalize afidelity-utility gap: common generative objectives prioritize distributional plausibility, whereas augmentation succeeds only when injected samples reduce the current learner’s held-out evaluation loss. This gap motivates learning not just how to generate, but what to generate and when to inject as training evolves. We propose TAP (Tabular Augmentation Policy), which couplesdiffusion inpaintingwith a lightweight,learner-conditioned policyto steer generation toward high-utility regions and controls safe injection viaexplicit gatingandconservative windowed commitment. Under severe data scarcity, TAP consistently outperforms strong generative baselines on seven real-world datasets, improving classification accuracy by up to 15.6 percentage points and reducing regression RMSE by up to 32%.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2605\.10315

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.10315 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.10315 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.10315 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Geometry-Aware Tabular Diffusion

arXiv cs.LG

Introduces Geometry-Aware Tabular Diffusion (GATD), which augments tabular diffusion denoisers with explicit pairwise geometric features. Achieves state-of-the-art performance on ten benchmarks while using significantly fewer parameters.

From Noise to Control: Parameterized Diffusion Policies

arXiv cs.AI

This paper introduces Parameterized Diffusion Policy (PDP), a framework that makes diffusion policies controllable by conditioning on low-dimensional latent parameters, enabling smooth behavior interpolation and adaptation without retraining. It demonstrates improved performance on complex multimodal robot tasks in simulation and real-world experiments.