LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning
This addresses the risk of harmful content generation in AI models, offering an incremental improvement for machine unlearning techniques.
The paper tackles the problem of machine unlearning (MU) for generative models, where existing methods struggle with data that is harder to unlearn, and introduces LoReUn, a plug-and-play strategy that dynamically reweights data based on loss, reducing the gap to exact unlearning by up to 30% in image classification and generation tasks.
Recent generative models face significant risks of producing harmful content, which has underscored the importance of machine unlearning (MU) as a critical technique for eliminating the influence of undesired data. However, existing MU methods typically assign the same weight to all data to be forgotten, which makes it difficult to effectively forget certain data that is harder to unlearn than others. In this paper, we empirically demonstrate that the loss of data itself can implicitly reflect its varying difficulty. Building on this insight, we introduce Loss-based Reweighting Unlearning (LoReUn), a simple yet effective plug-and-play strategy that dynamically reweights data during the unlearning process with minimal additional computational overhead. Our approach significantly reduces the gap between existing MU methods and exact unlearning in both image classification and generation tasks, effectively enhancing the prevention of harmful content generation in text-to-image diffusion models.