Latent Diffusion for Missing Data

2026-05-27

AI Summary

This work addresses the significant performance degradation of existing diffusion models under high rates of randomly missing data and the artifact-inducing nature of zero-filling imputation. The authors propose a two-stage latent-space diffusion framework: first, a robust variational autoencoder (VAE) extracts compact semantic features from incomplete observations; then, a diffusion model is trained in the latent space for both generation and imputation. This approach provides the first systematic validation that latent-space diffusion modeling effectively mitigates artifact amplification, enabling end-to-end training under the missing completely at random (MCAR) assumption. Experimental results demonstrate that the method generates high-quality samples even with 50% missing data and substantially outperforms pixel-space diffusion approaches in imputation accuracy.

Abstract

Diffusion models have emerged as powerful generative approaches for missing-data imputation, yet most existing methods operate directly in data space and degrade when training data are heavily incomplete. We investigate whether shifting diffusion to a learned latent representation improves robustness under missing-completely-at-random (MCAR) corruption. To this end, we propose a two-stage framework: a robust VAE-based imputer first learns compact semantic features from incomplete observations, and a diffusion model is then trained in the resulting latent space. Across training missing rates, we perform a controlled comparison against pixel-space diffusion models under the same incomplete-data setting. The latent diffusion model maintains high sample quality and remains stable up to 50\% missingness, while pixel-space diffusion degrades progressively as missingness increases. For downstream imputation, latent diffusion also achieves consistently better performance than pixel-space diffusion. These findings indicate that latent-space modeling mitigates artifact amplification from zero-imputed inputs and provides a more robust generative prior for incomplete-data learning. Overall, our results support latent diffusion as a strong and practically useful alternative to pixel-space diffusion for missing-data problems.

Problem

• missing data
• diffusion models
• latent space
• imputation
• data incompleteness

Innovation

• latent diffusion
• missing data imputation
• variational autoencoder
• generative modeling
• MCAR