mlsanityData to 14 Oct 2026

Controllable Machine Unlearning via Gradient Pivoting

arXiv 2510.19226 ↗First posted 22 Oct 2025cs.LG math.OCcited by 0

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Machine unlearning (MU) aims to remove the influence of specific data from a trained model. However, approximate unlearning methods, often formulated as a single-objective optimization (SOO) problem, face a critical trade-off between unlearning efficacy and model fidelity. This leads to three primary challenges: the risk of over-forgetting, a lack of fine-grained control over the unlearning process, and the absence of metrics to holistically evaluate the trade-off. To address these issues, we reframe MU as a multi-objective optimization (MOO) problem. We then introduce a novel algorithm, Controllable Unlearning by Pivoting Gradient (CUP), which features a unique pivoting mechanism. Unlike traditional MOO methods that converge to a single solution, CUP's mechanism is designed to controllably navigate the entire Pareto frontier. This navigation is governed by a single intuitive hyperparameter, the `unlearning intensity', which allows for precise selection of a desired trade-off. To evaluate this capability, we adopt the hypervolume indicator, a metric that captures both the quality and diversity of the entire set of solutions an algorithm can generate. Our experimental results demonstrate that CUP produces a superior set of Pareto-optimal solutions, consistently outperforming existing methods across various vision tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 31 of its 42 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

31 of 42 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024A Closer Look at Machine Unlearning for Large Language Models10 Oct
  2. 2024Adversarial Machine Unlearning11 Jun
  3. 2024Machine Unlearning via Null Space Calibration21 Apr
  4. 2023Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation28 Dec
  5. 2023Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection7 Dec
  6. 2023Fast Model Debias with Machine Unlearning19 Oct
  7. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation19 Oct
  8. 2023Fair Machine Unlearning: Data Removal while Mitigating Disparities27 Jul
  9. 2023Model Sparsity Can Simplify Machine Unlearning11 Apr
  10. 2023Boundary Unlearning21 Mar
  11. 2023To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods7 Feb
  12. 2023Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers27 Jan
2 more
  1. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearning27 Sep
  2. 2021Hard to Forget: Poisoning Attacks on Certified Machine Unlearning17 Sep

Other references · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  6. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  7. 2023Erasing Concepts from Diffusion Modelscited by 539
  8. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 513
  9. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 465
  10. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 317
  11. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Modelscited by 301
  12. 2020Approximate Data Deletion from Machine Learning Modelscited by 255
5 more
  1. 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Modelscited by 177
  2. 2024Machine Unlearning for Image-to-Image Generative Modelscited by 47
  3. 2022Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attackscited by 43
  4. 2024Dual Cone Gradient Descent for Training Physics-Informed Neural Networkscited by 21
  5. 2023Gradient Surgery for One-shot Unlearning on Generative Modelcited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery
  2. 2024MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes
  3. 2024nabla τ: Gradient-based and Task-Agnostic machine Unlearning
  4. 2025Machine Unlearning under Overparameterization
  5. 2026Multi-Objective Reference-Aligned Machine Unlearning
  6. 2024Remaining-data-free Machine Unlearning by Suppressing Sample Contribution
  7. 2024A More Practical Approach to Machine Unlearning
  8. 2024Learning to Unlearn for Robust Machine Unlearning