REVIEW 4 cited by
MissDiff: Training Diffusion Models on Tabular Data with Missing Values
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The diffusion model has shown remarkable performance in modeling data distributions and synthesizing data. However, the vanilla diffusion model requires complete or fully observed data for training. Incomplete data is a common issue in various real-world applications, including healthcare and finance, particularly when dealing with tabular datasets. This work presents a unified and principled diffusion-based framework for learning from data with missing values under various missing mechanisms. We first observe that the widely adopted "impute-then-generate" pipeline may lead to a biased learning objective. Then we propose to mask the regression loss of Denoising Score Matching in the training phase. We prove the proposed method is consistent in learning the score of data distributions, and the proposed training objective serves as an upper bound for the negative likelihood in certain cases. The proposed framework is evaluated on multiple tabular datasets using realistic and efficacious metrics and is demonstrated to outperform state-of-the-art diffusion model on tabular data with "impute-then-generate" pipeline by a large margin.
Forward citations
Cited by 4 Pith papers
-
Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion
Gradients of any differentiable tabular constraint lie in the tangent space of the data manifold, enabling a single trained diffusion model to satisfy unseen conditions via inference-time guidance.
-
Flow Matching with Missing Data
Resampling missing coordinates and averaging the flow-matching loss reproduces the complete-data objective exactly under MCAR with oracle completions; one completion per example is optimal for a fixed budget.
-
Watermarking Generative Categorical Data
A distribution-level watermark for categorical data, embedded by secret hashing and detected by inverting the hash mixture and comparing total variation distance to the original distribution.
-
Interpolation pour l'augmentation de donnees : Application \`a la gestion des adventices de la canne a sucre a la Reunion
Interpolation-based data augmentation using Gaussian processes with combined kernels improves regression accuracy for sugarcane weed coverage more efficiently than kriging, at the cost of spatial homogeneity.
Discussion (0). Continue with ORCID to comment.