Hugging Face Daily Papers · · 3 min read

Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

TAP: Active Tabular Augmentation via Policy-Guided Diffusion Inpainting</p>\n","updatedAt":"2026-05-14T18:59:56.867Z","author":{"_id":"64c5a77f725ffa04b2ebd482","avatarUrl":"/avatars/b764e36e6bfe23ffc7eb40bfd3c3200f.svg","fullname":"Zheyu Zhang","name":"oooranz","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.8942532539367676},"editors":["oooranz"],"editorAvatarUrls":["/avatars/b764e36e6bfe23ffc7eb40bfd3c3200f.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.10315","authors":[{"_id":"6a04e0f0b1a8cbabc9f085c8","name":"Zheyu Zhang","hidden":false},{"_id":"6a04e0f0b1a8cbabc9f085c9","name":"Shuo Yang","hidden":false},{"_id":"6a04e0f0b1a8cbabc9f085ca","name":"Bardh Prenkaj","hidden":false},{"_id":"6a04e0f0b1a8cbabc9f085cb","name":"Gjergji Kasneci","hidden":false}],"publishedAt":"2026-05-11T00:00:00.000Z","submittedOnDailyAt":"2026-05-14T00:00:00.000Z","title":"Active Tabular Augmentation via Policy-Guided Diffusion Inpainting","submittedOnDailyBy":{"_id":"64c5a77f725ffa04b2ebd482","avatarUrl":"/avatars/b764e36e6bfe23ffc7eb40bfd3c3200f.svg","isPro":false,"fullname":"Zheyu Zhang","user":"oooranz","type":"user","name":"oooranz"},"summary":"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%.","upvotes":0,"discussionId":"6a04e0f1b1a8cbabc9f085cc","ai_summary":"Tabular augmentation policy combines diffusion inpainting with a learner-conditioned policy to improve downstream model performance under data scarcity.","ai_keywords":["generative tabular augmentation","distributional fidelity","fidelity-utility gap","diffusion inpainting","learner-conditioned policy","explicit gating","conservative windowed commitment","tabular augmentation policy","data-scarce domains"],"organization":{"_id":"61fae781e68759322b9767be","name":"TUM","fullname":"Technical University of Munich","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1661167219960-629521a0f937190946e15d7f.jpeg"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"],"organization":{"_id":"61fae781e68759322b9767be","name":"TUM","fullname":"Technical University of Munich","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1661167219960-629521a0f937190946e15d7f.jpeg"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.10315.md"}">
Papers
arxiv:2605.10315

Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

Published on May 11
· Submitted by
Zheyu Zhang
on May 14
Authors:
,
,
,

Abstract

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

AI-generated summary

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%.

Community

TAP: Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

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 paper 0

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 paper 0

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 paper 0

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 paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers