mlsanityData to 7 Oct 2026

Approximate Data Deletion from Machine Learning Models

arXiv 2002.10077 ↗First posted 24 Feb 2020cs.LG stat.MLcited by 250

Not on the map. Why?

Cited by 204 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deleting data from a trained machine learning (ML) model is a critical task in many applications. For example, we may want to remove the influence of training points that might be out of date or outliers. Regulations such as EU's General Data Protection Regulation also stipulate that individuals can request to have their data deleted. The naive approach to data deletion is to retrain the ML model on the remaining data, but this is too time consuming. In this work, we propose a new approximate deletion method for linear and logistic models whose computational cost is linear in the the feature dimension d and independent of the number of training data n. This is a significant gain over all existing methods, which all have superlinear time dependence on the dimension. We also develop a new feature-injection test to evaluate the thoroughness of data deletion from ML models.

Key facts. Cited by 250 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 26; 2023: 42; 2024: 69; 2025: 59; 2026: 41.

250 papers.

Sort:

By area:

  1. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearningcited by 484
  2. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 376
  3. 2023Detecting Pretraining Data from Large Language Modelscited by 375
  4. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
  5. 2022A Survey of Machine Unlearningcited by 298
  6. 2023Large Language Model Unlearningcited by 288
  7. 2023Towards Unbounded Machine Unlearningcited by 261
  8. 2024MUSE: Machine Unlearning Six-Way Evaluation for Language Modelscited by 251
  9. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  10. 2023In-Context Unlearning: Language Models as Few Shot Unlearnerscited by 214
  11. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMscited by 211
  12. 2021Fast Yet Effective Machine Unlearningcited by 209
38 more
  1. 2023Model Sparsity Can Simplify Machine Unlearningcited by 206
  2. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teachercited by 189
  3. 2022If Influence Functions are the Answer, Then What is the Question?cited by 142
  4. 2021Graph Unlearningcited by 129
  5. 2021Machine Unlearning via Algorithmic Stabilitycited by 128
  6. 2022Zero-Shot Machine Unlearningcited by 125
  7. 2022Measuring Forgetting of Memorized Training Examplescited by 118
  8. 2024Machine Unlearning of Pre-trained Large Language Modelscited by 118
  9. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retrainingcited by 109
  10. 2021Federated Unlearning via Class-Discriminative Pruningcited by 108
  11. 2024SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearningcited by 104
  12. 2024What makes unlearning hard and what to do about itcited by 89
  13. 2023Machine Unlearning: Solutions and Challengescited by 85
  14. 2022Deep Unlearning via Randomized Conditionally Independent Hessianscited by 83
  15. 2022Towards Adversarial Evaluations for Inexact Machine Unlearningcited by 82
  16. 2024Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacycited by 78
  17. 2022Recommendation Unlearningcited by 71
  18. 2024LLM Unlearning via Loss Adjustment with Only Forget Datacited by 71
  19. 2022Federated Unlearning with Knowledge Distillationcited by 70
  20. 2023Fast Model Debias with Machine Unlearningcited by 70
  21. 2023GIF: A General Graph Unlearning Strategy via Influence Functioncited by 59
  22. 2022Forget Unlearning: Towards True Data-Deletion in Machine Learningcited by 58
  23. 2024Scissorhands: Scrub Data Influence via Connection Sensitivity in Networkscited by 50
  24. 2024UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Modelscited by 47
  25. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  26. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  27. 2024Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearningcited by 44
  28. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
  29. 2024Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancementcited by 43
  30. 2021Certifiable Machine Unlearning for Linear Modelscited by 42
  31. 2022Algorithms that Approximate Data Removal: New Results and Limitationscited by 39
  32. 2025Exploring Criteria of Loss Reweighting to Enhance LLM Unlearningcited by 39
  33. 2022Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attackscited by 37
  34. 2023Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projectioncited by 37
  35. 2024Machine Unlearning Fails to Remove Data Poisoning Attackscited by 35
  36. 2024Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspectivecited by 33
  37. 2022Deep Regression Unlearningcited by 32
  38. 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30

50 most cited of 250 All 250 (JSON)