mlsanityData to 7 Oct 2026

Machine Unlearning via Null Space Calibration

arXiv 2404.13588 ↗First posted 21 Apr 2024cs.LG cs.AIcited by 19

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Machine unlearning aims to enable models to forget specific data instances when receiving deletion requests. Current research centres on efficient unlearning to erase the influence of data from the model and neglects the subsequent impacts on the remaining data. Consequently, existing unlearning algorithms degrade the model's performance after unlearning, known as textitover-unlearning. This paper addresses this critical yet under-explored issue by introducing machine underlineUnlearning via underlineNull underlineSpace underlineCalibration (UNSC), which can accurately unlearn target samples without over-unlearning. On the contrary, by calibrating the decision space during unlearning, UNSC can significantly improve the model's performance on the remaining samples. In particular, our approach hinges on confining the unlearning process to a specified null space tailored to the remaining samples, which is augmented by strategically pseudo-labeling the unlearning samples. Comparative analyses against several established baselines affirm the superiority of our approach. Code is released at this hrefhttps://github.com/HQC-ML/Machine-Unlearning-via-Null-Space-CalibrationURL.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 23 of its 32 references that are in the map. First posted on arXiv 21 Apr 2024.

Builds on

23 of 32 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation19 Oct
  2. 2023A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services15 Sep
  3. 2023Boundary Unlearning21 Mar

Other references · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  6. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  7. 2019Machine Unlearningcited by 1,020
  8. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  9. 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 784
  10. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  11. 2019Certified Data Removal from Machine Learning Modelscited by 512
  12. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
8 more
  1. 2018Measuring the Intrinsic Dimension of Objective Landscapescited by 364
  2. 2019Orthogonal Gradient Descent for Continual Learningcited by 361
  3. 2021Gradient Projection Memory for Continual Learningcited by 338
  4. 2020Amnesiac Machine Learningcited by 305
  5. 2018Gradient Descent Happens in a Tiny Subspacecited by 208
  6. 2021Training Networks in Null Space of Feature Covariance for Continual Learningcited by 139
  7. 2020Certified Robustness to Label-Flipping Attacks via Randomized Smoothingcited by 103
  8. 2020Selective Forgetting of Deep Networks at a Finer Level than Samplescited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 12; 2026: 4.

19 papers.

Sort:

By area:

  1. 2024Machine Unlearning Fails to Remove Data Poisoning Attackscited by 35
  2. 2025SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Modelscited by 33
  3. 2025Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocolscited by 16
  4. 2024Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoningcited by 5
  5. 2024Toward Efficient Data-Free Unlearningcited by 4
  6. 2025Machine Unlearning under Overparameterizationcited by 4
  7. 2025Geometric-disentangelment Unlearningcited by 4
  8. 2025Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attackcited by 3
  9. 2025Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approachcited by 2
  10. 2026Erase at the Core: Representation Unlearning for Machine Unlearningcited by 2
  11. 2025Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacycited by 1
  12. 2025Zero-Shot Machine Unlearning with Proxy Adversarial Data Generationcited by 1
7 more
  1. 2025Soft Weighted Machine Unlearningcited by 0
  2. 2025COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinementcited by 0
  3. 2025FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairnesscited by 0
  4. 2025Controllable Machine Unlearning via Gradient Pivotingcited by 0
  5. 2026Retain-Neutral Surrogates for Min-Max Unlearningcited by 0
  6. 2026Spectral Saliency for Machine Unlearningcited by 0
  7. 2026Unmerge: Efficient Machine Unlearning via Task Arithmeticcited by 0