# Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

arXiv: https://arxiv.org/abs/2605.10315 · HTML: https://mlsanity.com/paper/2605.10315/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 33 of its 57 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 30 of 33)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Neural Spline Flows](https://mlsanity.com/paper/1906.04032/) (2019)
- [Tabular Data: Deep Learning is Not All You Need](https://mlsanity.com/paper/2106.03253/) (2021)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Data Augmentation Can Improve Robustness](https://mlsanity.com/paper/2111.05328/) (2021)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [OpenML Benchmarking Suites](https://mlsanity.com/paper/1708.03731/) (2017)
- [TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation](https://mlsanity.com/paper/2410.20626/) (2024)
- [Transfer Learning with Deep Tabular Models](https://mlsanity.com/paper/2206.15306/) (2022)
- [Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes](https://mlsanity.com/paper/2312.12112/) (2023)
- [Adversarial random forests for density estimation and generative modeling](https://mlsanity.com/paper/2205.09435/) (2022)
- [Contrastive Mixup: Self- and Semi-Supervised learning for Tabular Domain](https://mlsanity.com/paper/2108.12296/) (2021)
- [TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models](https://mlsanity.com/paper/2409.16118/) (2024)
- [Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI](https://mlsanity.com/paper/2407.21523/) (2024)
- [On the Usefulness of Synthetic Tabular Data Generation](https://mlsanity.com/paper/2306.15636/) (2023)
- [Rethinking Data Augmentation for Tabular Data in Deep Learning](https://mlsanity.com/paper/2305.10308/) (2023)
- [Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs](https://mlsanity.com/paper/2507.19334/) (2025)

## Built on by (most cited first, 1 of 1)

- [Relational Learning as World Modeling](https://mlsanity.com/paper/2610.16763/) (2026)

## Abstract (arXiv)

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%.