基于不确定性的遗忘：面向量化神经网络的正交熵遗忘
Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks
AI总结：
针对量化模型中的机器遗忘问题，提出正交熵遗忘框架（OEU），通过熵引导无偏遗忘和梯度正交投影消除梯度冲突，兼顾遗忘效果与模型效用。
摘要：
量化神经网络在边缘设备上的部署，结合GDPR等隐私法规，迫切需要在量化模型中进行机器遗忘。然而，现有方法面临关键挑战：它们通过训练模型记忆错误标签来诱导遗忘，将遗忘与错误记忆混为一谈，并采用标量梯度重加权，无法解决梯度之间的方向冲突。我们提出OEU，一种新颖的正交熵遗忘框架，具有两个关键创新：1）熵引导遗忘通过最大化遗忘数据上的预测不确定性提供无偏遗忘方向，避免向任何特定类别的错误预测；2）梯度正交投影通过将遗忘梯度投影到保留梯度的正交补上来消除干扰，在一阶近似下为效用保持提供理论保证。大量实验表明，OEU在遗忘效果和保留准确率上均优于现有方法。
英文摘要：
The deployment of quantized neural networks on edge devices, combined with privacy regulations like GDPR, creates an urgent need for machine unlearning in quantized models. However, existing methods face critical challenges: they induce forgetting by training models to memorize incorrect labels, conflating forgetting with misremembering, and employ scalar gradient reweighting that cannot resolve directional conflicts between gradients. We propose OEU, a novel Orthogonal Entropy Unlearning framework with two key innovations: 1) Entropy-guided unlearning provides an unbiased forgetting direction by maximizing prediction uncertainty on forgotten data, avoiding confident misprediction toward any specific class, and 2) Gradient orthogonal projection eliminates interference by projecting forgetting gradients onto the orthogonal complement of retain gradients, providing theoretical guarantees for utility preservation under first-order approximation. Extensive experiments demonstrate that OEU outperforms existing methods in both forgetting effectiveness and retain accuracy.
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。
