English

The Journey, Not the Destination: How Data Guides Diffusion Models

Computer Vision and Pattern Recognition 2023-12-12 v1 Machine Learning

Abstract

Diffusion models trained on large datasets can synthesize photo-realistic images of remarkable quality and diversity. However, attributing these images back to the training data-that is, identifying specific training examples which caused an image to be generated-remains a challenge. In this paper, we propose a framework that: (i) provides a formal notion of data attribution in the context of diffusion models, and (ii) allows us to counterfactually validate such attributions. Then, we provide a method for computing these attributions efficiently. Finally, we apply our method to find (and evaluate) such attributions for denoising diffusion probabilistic models trained on CIFAR-10 and latent diffusion models trained on MS COCO. We provide code at https://github.com/MadryLab/journey-TRAK .

Keywords

Cite

@article{arxiv.2312.06205,
  title  = {The Journey, Not the Destination: How Data Guides Diffusion Models},
  author = {Kristian Georgiev and Joshua Vendrow and Hadi Salman and Sung Min Park and Aleksander Madry},
  journal= {arXiv preprint arXiv:2312.06205},
  year   = {2023}
}

Comments

29 pages, 17 figures

R2 v1 2026-06-28T13:46:49.740Z