A Unified Framework for Diffusion Model Unlearning with f-Divergence

Nicola Novello, Federico Fontana, Luigi Cinque, Deniz Gunduz, Andrea M Tonello

Keywords: machine unlearning, diffusion models, f-divergence

Abstract:

Machine unlearning aims to remove specific knowledge from a trained model. While diffusion models (DMs) have shown remarkable generative capabilities, existing unlearning methods for text-to-image (T2I) models often rely on minimizing the mean squared error (MSE) between the output distribution of a target and an anchor concept.
We show that this MSE-based approach is a special case of a unified $f$-divergence-based framework, in which any $f$-divergence can be utilized.
We analyze the benefits of using different $f$-divergences, that mainly impact the convergence properties of the algorithm and the quality of unlearning.
The proposed unified framework offers a flexible paradigm that allows to select the optimal divergence for a specific application, balancing different trade-offs between aggressive unlearning and concept preservation.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 24471