# Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels

arXiv: https://arxiv.org/abs/2503.13917 · HTML: https://mlsanity.com/paper/2503.13917/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 27 of its 31 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [ZeroQ: A Novel Zero Shot Quantization Framework](https://mlsanity.com/paper/2001.00281/) (2020)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks](https://mlsanity.com/paper/1908.05033/) (2019)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [LSQ+: Improving low-bit quantization through learnable offsets and better initialization](https://mlsanity.com/paper/2004.09576/) (2020)
- [Generative Low-bitwidth Data Free Quantization](https://mlsanity.com/paper/2003.03603/) (2020)
- [Post-Training Piecewise Linear Quantization for Deep Neural Networks](https://mlsanity.com/paper/2002.00104/) (2020)
- [Adaptive Quantization for Deep Neural Network](https://mlsanity.com/paper/1712.01048/) (2017)
- [Diversifying Sample Generation for Accurate Data-Free Quantization](https://mlsanity.com/paper/2103.01049/) (2021)
- [Certified Graph Unlearning](https://mlsanity.com/paper/2206.09140/) (2022)

## Built on by (most cited first, 12 of 12)

- [SAGE: Accelerating Vision-Language Models via Entropy-Guided Adaptive Speculative Decoding](https://mlsanity.com/paper/2602.00523/) (2026)
- [LetheViT: Selective Machine Unlearning for Vision Transformers via Attention-Guided Contrastive Learning](https://mlsanity.com/paper/2508.01569/) (2025)
- [Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks](https://mlsanity.com/paper/2602.00567/) (2026)
- [Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study](https://mlsanity.com/paper/2512.19253/) (2025)
- [CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic](https://mlsanity.com/paper/2605.18610/) (2026)
- [Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction](https://mlsanity.com/paper/2606.01850/) (2026)
- [QUAIL: Quantization Aware Unlearning for Mitigating Misinformation in LLMs](https://mlsanity.com/paper/2601.15538/) (2026)
- [A Note on Stability for Orthogonalized Matrix Momentum with Client Sampling](https://mlsanity.com/paper/2606.01720/) (2026)
- [Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction](https://mlsanity.com/paper/2609.27355/) (2026)
- [FiCABU: A Fisher-Based, Context-Adaptive Machine Unlearning Processor for Edge AI](https://mlsanity.com/paper/2511.05605/) (2025)
- [SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution](https://mlsanity.com/paper/2602.00577/) (2026)
- [TRACE: Transition-Aware Residual Control for Multi-Objective Materials Discovery](https://mlsanity.com/paper/2608.23631/) (2026)

## Abstract (arXiv)

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.