A Unified Framework for Diffusion Model Unlearning with f-Divergence
Nicola Novello, Federico Fontana, Luigi Cinque, Deniz Gunduz, Andrea Tonello
Abstract
Most current methods for unlearning concepts in text-to-image diffusion models rely on mean squared error-based loss functions to align target distributions with anchors. In this paper, we generalize this idea into a unified $f$-divergence-based framework that recovers the standard mean squared error loss as a specific instance. By generalizing the loss function, we theoretically analyze and numerically validate how different $f$-divergences impact the gradient magnitude and the convergence properties of the algorithm, affecting the quality of unlearning. The proposed unified framework offers a flexible paradigm for selecting the optimal divergence based on the application and user goal, allowing for finer control over the trade-off between unlearning efficacy and generative fidelity.
BibTeX
@inproceedings{
novello2026a,
title={A Unified Framework for Diffusion Model Unlearning with f-Divergence},
author={Nicola Novello and Federico Fontana and Luigi Cinque and Deniz Gunduz and Andrea M Tonello},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=6kyKD3bVi6}
}