Search papers, labs, and topics across Lattice.
This paper introduces PECKER, a machine unlearning method for diffusion models that uses a saliency mask to prioritize gradient updates to parameters most relevant to the data being forgotten. By focusing updates, PECKER reduces unnecessary computation and improves training efficiency within a distillation framework. Experiments on CIFAR-10 and STL-10 demonstrate that PECKER achieves faster unlearning of classes and concepts while maintaining image quality, outperforming existing methods in terms of training time.
Forget entire image classes from your diffusion model faster and more efficiently with a targeted parameter update strategy.
Machine unlearning (MU) has become a critical technique for GenAI models'safe and compliant operation. While existing MU methods are effective, most impose prohibitive training time and computational overhead. Our analysis suggests the root cause lies in poorly directed gradient updates, which reduce training efficiency and destabilize convergence. To mitigate these issues, we propose PECKER, an efficient MU approach that matches or outperforms prevailing methods. Within a distillation framework, PECKER introduces a saliency mask to prioritize updates to parameters that contribute most to forgetting the targeted data, thereby reducing unnecessary gradient computation and shortening overall training time without sacrificing unlearning efficacy. Our method generates samples that unlearn related class or concept more quickly, while closely aligning with the true image distribution on CIFAR-10 and STL-10 datasets, achieving shorter training times for both class forgetting and concept forgetting.
