针对量化模型设计的鲁棒去学习方法，解决遗忘与保留数据梯度失衡问题。
Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels
- 用语义一致的相似标签替代随机标签，减少噪声注入
- 动态调整梯度权重，平衡遗忘与保留数据的更新贡献
- 首个专为量化模型设计的去学习框架，适合边缘设备部署
模型量化通过低比特参数表示实现深度神经网络在边缘设备上的高效部署，但给符合数据隐私法规的机器去学习（MU）带来挑战。现有为全精度模型设计的去学习方法无法解决量化网络中的两个根本问题：1）数据处理中因标签不匹配导致的噪声放大；2）遗忘与保留数据在训练过程中梯度失衡。这些问题在参数空间受限、优化离散的量化模型中尤为严重。本文提出Q-MUL，首个专为量化模型设计的去学习框架。方法引入两项关键创新：1）相似标签分配，用语义一致的替代标签取代随机标签以最小化噪声注入；2）自适应梯度重加权，动态对齐遗忘与保留数据的参数更新贡献。通过系统分析量化模型的脆弱性，建立了这些机制的理论基础。在基准数据集上的广泛实验表明，Q-MUL显著优于现有方法。
原文摘要 · Abstract (English)
Model quantization enables efficient deployment of deep neural networks on edge devices through low-bit parameter representation, yet raises critical challenges for implementing machine unlearning (MU) under data privacy regulations. Existing MU methods designed for full-precision models fail to address two fundamental limitations in quantized networks: 1) Noise amplification from label mismatch during data processing, and 2) Gradient imbalance between forgotten and retained data during training. These issues are exacerbated by quantized models' constrained parameter space and discrete optimization. We propose Q-MUL, the first dedicated unlearning framework for quantized models. Our method introduces two key innovations: 1) Similar Labels assignment replaces random labels with semantically consistent alternatives to minimize noise injection, and 2) Adaptive Gradient Reweighting dynamically aligns parameter update contributions from forgotten and retained data. Through systematic analysis of quantized model vulnerabilities, we establish theoretical foundations for these mechanisms. Extensive evaluations on benchmark datasets demonstrate Q-MUL's superiority over existing approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。