Measuring Semantic Information Production in Generative Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Handke, Florian, Koulischer, Félix, Raya, Gabriel, Ambrogioni, Luca
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918056646672384
author Handke, Florian
Koulischer, Félix
Raya, Gabriel
Ambrogioni, Luca
author_facet Handke, Florian
Koulischer, Félix
Raya, Gabriel
Ambrogioni, Luca
contents It is well known that semantic and structural features of the generated images emerge at different times during the reverse dynamics of diffusion, a phenomenon that has been connected to physical phase transitions in magnets and other materials. In this paper, we introduce a general information-theoretic approach to measure when these class-semantic "decisions" are made during the generative process. By using an online formula for the optimal Bayesian classifier, we estimate the conditional entropy of the class label given the noisy state. We then determine the time intervals corresponding to the highest information transfer between noisy states and class labels using the time derivative of the conditional entropy. We demonstrate our method on one-dimensional Gaussian mixture models and on DDPM models trained on the CIFAR10 dataset. As expected, we find that the semantic information transfer is highest in the intermediate stages of diffusion while vanishing during the final stages. However, we found sizable differences between the entropy rate profiles of different classes, suggesting that different "semantic decisions" are located at different intermediate times.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10433
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Measuring Semantic Information Production in Generative Diffusion Models
Handke, Florian
Koulischer, Félix
Raya, Gabriel
Ambrogioni, Luca
Machine Learning
It is well known that semantic and structural features of the generated images emerge at different times during the reverse dynamics of diffusion, a phenomenon that has been connected to physical phase transitions in magnets and other materials. In this paper, we introduce a general information-theoretic approach to measure when these class-semantic "decisions" are made during the generative process. By using an online formula for the optimal Bayesian classifier, we estimate the conditional entropy of the class label given the noisy state. We then determine the time intervals corresponding to the highest information transfer between noisy states and class labels using the time derivative of the conditional entropy. We demonstrate our method on one-dimensional Gaussian mixture models and on DDPM models trained on the CIFAR10 dataset. As expected, we find that the semantic information transfer is highest in the intermediate stages of diffusion while vanishing during the final stages. However, we found sizable differences between the entropy rate profiles of different classes, suggesting that different "semantic decisions" are located at different intermediate times.
title Measuring Semantic Information Production in Generative Diffusion Models
topic Machine Learning
url https://arxiv.org/abs/2506.10433