Research map / Image generation / Fast diffusion sampling

Conditional Diffusion with Ordinal Regression: Longitudinal Data Generation for Neurodegenerative Disease Studies

ICLR 2025 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a conditional diffusion model with ordinal regression for generating longitudinal neurodegenerative disease data (e.g., Alzheimer's) that handles irregular, large visit intervals.

Problem

Modeling neurodegenerative disease progression such as Alzheimer's disease is hard because longitudinal data are scarce and visits are irregularly spaced with large intervals between them.

Approach

Combines a conditional diffusion model with ordinal regression so that generated longitudinal samples respect the ordered disease-stage structure and can be conditioned on irregular time intervals between visits.

Closest papers by meaning

• Unscrambling disease progression at scale: fast inference of event permutations with optimal transport (NeurIPS 2024 · similarity 0.89)
• Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain Trajectories (ICLR 2025 · similarity 0.86)
• Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints (AAAI 2025 · similarity 0.85)
• CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation (NeurIPS 2026 · similarity 0.85)
• Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization (ICML 2024 · similarity 0.85)
• Uncertainty-Calibrated Prediction of Randomly-Timed Biomarker Trajectories with Conformal Bands (NeurIPS 2025 · similarity 0.85)