analiza aiqbench
AugMask addresses the gap between diffusion models and real-world tabular data by adapting missing-unaware backbones through stochastic augmentation and masked supervision. By treating imputed values as uncertain context rather than training targets, the method achieves superior performance across diverse missingness regimes without requiring specialized architectures. This approach offers a practical pathway for deploying generative models on incomplete datasets, a common challenge in practical machine learning applications.
AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking
arXiv:2606.03347v1 Announce Type: cross Abstract: Score-based diffusion models have emerged as prominent deep generative models; however, their application to tabular data remains challenging because their backbones assume fully specified inputs, whereas real-world tabular data often contain missing values. We propose AugMask, a plug-and-play training framework that adapts missing-unaware backbones to incomplete data by separating conditioning from supervision. AugMask 1) constructs numeric inputs via conditional stochastic augmentation using lightweight auxiliary models, and 2) applies denoising supervision only to observed coordinates. In effect, augmented missing entries serve as uncertain conditioning context rather than training targets. We connect this training rule to a Rao--Blackwellized objective and show that marginalizing missing entries yields a variance-weighted sensitivity penalty, discouraging over-reliance on uncertain completions. Across diverse datasets and missingness regimes, AugMask enables standard diffusion-based tabular generators to outperform specialized missing-aware baselines.
Abstract:Score-based diffusion models have emerged as prominent deep generative models; however, their application to tabular data remains challenging because their backbones assume fully specified inputs, whereas real-world tabular data often contain missing values. We propose AugMask, a plug-and-play training framework that adapts missing-unaware backbones to incomplete data by separating conditioning from supervision. AugMask 1) constructs numeric inputs via conditional stochastic augmentation using lightweight auxiliary models, and 2) applies denoising supervision only to observed coordinates. In effect, augmented missing entries serve as uncertain conditioning context rather than training targets. We connect this training rule to a Rao--Blackwellized objective and show that marginalizing missing entries yields a variance-weighted sensitivity penalty, discouraging over-reliance on uncertain completions. Across diverse datasets and missingness regimes, AugMask enables standard diffusion-based tabular generators to outperform specialized missing-aware baselines.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
arXiv:2606.03347 [cs.LG]
(or arXiv:2606.03347v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.03347 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 · 230 cuvinte
Subiecte conexe
TabMosaic: Unified In-Context Diffusion for Tabular Generative Tasks
arXiv · 15 oct. 2026
CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data
arXiv · 1 oct. 2026
SpatialCrafter: Single Image World Modeling with Generative 3D Proxies
arXiv · 28 aug. 2026
Conditioning Tree-Based Diffusions and Flows for Probabilistic Tabular Regression
arXiv · 3 aug. 2026