학술논문

EraseDiff: Erasing Data Influence in Diffusion Models
Document Type
Working Paper
Source
Subject
Computer Science - Computer Vision and Pattern Recognition
Language
Abstract
We introduce EraseDiff, an unlearning algorithm designed for diffusion models to address concerns related to data memorization. Our approach formulates the unlearning task as a constrained optimization problem, aiming to preserve the utility of the diffusion model on retained data while removing the information associated with the data to be forgotten. This is achieved by altering the generative process to deviate away from the ground-truth denoising procedure. To manage the computational complexity inherent in the diffusion process, we develop a first-order method for solving the optimization problem, which has shown empirical benefits. Extensive experiments and thorough comparisons with state-of-the-art algorithms demonstrate that EraseDiff effectively preserves the model's utility, efficacy, and efficiency.
Comment: Diffusion Model, Machine Unlearning