FaLW: 一种面向遗忘的损失重新加权方法用于长尾撤销学习
FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
AI总结：
FaLW是一种面向遗忘的损失重新加权方法，用于解决长尾撤销学习中的异质和偏斜偏差问题，通过动态调整撤销强度提升性能。
摘要：
机器撤销学习旨在高效地从训练模型中移除特定数据的影响，这对于维护数据隐私法规如“被遗忘权”至关重要。然而，现有研究主要在相对平衡的遗忘集上评估撤销方法，这忽略了现实世界中常见的场景，即需要遗忘的数据（如用户的活动记录）遵循长尾分布。我们的工作首次探讨了这一关键研究空白。我们发现，在这种长尾设置中，现有方法面临两个关键问题：异质撤销偏差和偏斜撤销偏差。为了解决这些挑战，我们提出了FaLW，一种即插即用、实例级动态损失重新加权方法。FaLW创新性地通过将每个样本的预测概率与同类别未见过的数据分布进行比较，评估每个样本的撤销状态。基于此，它使用一种受平衡因子调制的遗忘感知重新加权方案，以适应性地调整每个样本的撤销强度。广泛的实验表明，FaLW实现了优越的性能。
英文摘要：
Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be forgotten". However, existing research predominantly evaluates unlearning methods on relatively balanced forget sets. This overlooks a common real-world scenario where data to be forgotten, such as a user's activity records, follows a long-tailed distribution. Our work is the first to investigate this critical research gap. We find that in such long-tailed settings, existing methods suffer from two key issues: \textit{Heterogeneous Unlearning Deviation} and \textit{Skewed Unlearning Deviation}. To address these challenges, we propose FaLW, a plug-and-play, instance-wise dynamic loss reweighting method. FaLW innovatively assesses the unlearning state of each sample by comparing its predictive probability to the distribution of unseen data from the same class. Based on this, it uses a forgetting-aware reweighting scheme, modulated by a balancing factor, to adaptively adjust the unlearning intensity for each sample. Extensive experiments demonstrate that FaLW achieves superior performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
