Machine Unlearning for Image-to-Image Generative Models
It addresses the need for data privacy compliance in generative AI, specifically for image-to-image models, representing a novel but incremental extension from classification to generative tasks.
The paper tackles the problem of machine unlearning for image-to-image generative models, which was previously unexplored, by proposing a computationally-efficient algorithm that effectively removes information from forget samples with negligible performance degradation on retain samples, as shown on datasets like ImageNet-1K and Places-365.
Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification models, leaving the landscape of unlearning for generative models relatively unexplored. This paper serves as a bridge, addressing the gap by providing a unifying framework of machine unlearning for image-to-image generative models. Within this framework, we propose a computationally-efficient algorithm, underpinned by rigorous theoretical analysis, that demonstrates negligible performance degradation on the retain samples, while effectively removing the information from the forget samples. Empirical studies on two large-scale datasets, ImageNet-1K and Places-365, further show that our algorithm does not rely on the availability of the retain samples, which further complies with data retention policy. To our best knowledge, this work is the first that represents systemic, theoretical, empirical explorations of machine unlearning specifically tailored for image-to-image generative models. Our code is available at https://github.com/jpmorganchase/l2l-generator-unlearning.