mlsanityData to 13 Oct 2026

Machine Unlearning: Linear Filtration for Logit-based Classifiers

arXiv 2002.02730 ↗First posted 7 Feb 2020cs.LG stat.MLcited by 95

Not on the map. Why?

Cited by 76 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recently enacted legislation grants individuals certain rights to decide in what fashion their personal data may be used, and in particular a "right to be forgotten". This poses a challenge to machine learning: how to proceed when an individual retracts permission to use data which has been part of the training process of a model? From this question emerges the field of machine unlearning, which could be broadly described as the investigation of how to "delete training data from models". Our work complements this direction of research for the specific setting of class-wide deletion requests for classification models (e.g. deep neural networks). As a first step, we propose linear filtration as a intuitive, computationally efficient sanitization method. Our experiments demonstrate benefits in an adversarial setting over naive deletion schemes.

Key facts. Cited by 95 papers in the map (data through 13 Oct 2026). First posted on arXiv 7 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 11; 2022: 13; 2023: 20; 2024: 31; 2025: 11; 2026: 9.

95 papers.

Sort:

By area:

  1. 2022A Survey of Machine Unlearningcited by 311
  2. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearningcited by 277
  3. 2021Fast Yet Effective Machine Unlearningcited by 216
  4. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 171
  5. 2021Graph Unlearningcited by 138
  6. 2022The Privacy Onion Effect: Memorization is Relativecited by 136
  7. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retrainingcited by 117
  8. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?cited by 95
  9. 2022Towards Adversarial Evaluations for Inexact Machine Unlearningcited by 83
  10. 2023Fast Model Debias with Machine Unlearningcited by 72
  11. 2024Scissorhands: Scrub Data Influence via Connection Sensitivity in Networkscited by 52
  12. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 51
38 more
  1. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  2. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
  3. 2023Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projectioncited by 37
  4. 2022Privacy Adhering Machine Un-learning in NLPcited by 36
  5. 2024Machine Unlearning: A Comprehensive Surveycited by 35
  6. 2023A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Servicescited by 34
  7. 2024Fast Exact Unlearning for In-Context Learning Data for LLMscited by 34
  8. 2024A Review on Machine Unlearningcited by 32
  9. 2022Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendationcited by 29
  10. 2024Continual Forgetting for Pre-trained Vision Modelscited by 29
  11. 2023SAFE: Machine Unlearning With Shard Graphscited by 28
  12. 2025Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Taskscited by 28
  13. 2022Verifiable and Provably Secure Machine Unlearningcited by 25
  14. 2023Deep Unlearning: Fast and Efficient Gradient-free Approach to Class Forgettingcited by 22
  15. 2022Knowledge Removal in Sampling-based Bayesian Inferencecited by 21
  16. 2021DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networkscited by 19
  17. 2022Few-Shot Unlearning by Model Inversioncited by 19
  18. 2023To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methodscited by 19
  19. 2023Machine Unlearning: A Surveycited by 19
  20. 2024Generative Unlearning for Any Identitycited by 19
  21. 2021A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communicationcited by 18
  22. 2023Subspace based Federated Unlearningcited by 17
  23. 2023Feature Unlearning for Pre-trained GANs and VAEscited by 16
  24. 2024Adversarial Machine Unlearningcited by 16
  25. 2022Bounding Membership Inferencecited by 15
  26. 2024A Survey on Machine Unlearning: Techniques and New Emerged Privacy Riskscited by 15
  27. 2025Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adaptercited by 15
  28. 2022An Introduction to Machine Unlearningcited by 13
  29. 2024Human-inspired Perspectives: A Survey on AI Long-term Memorycited by 12
  30. 2021Bounding Information Leakage in Machine Learningcited by 11
  31. 2023Generative Adversarial Networks Unlearningcited by 11
  32. 2024nabla τ: Gradient-based and Task-Agnostic machine Unlearningcited by 11
  33. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  34. 2024Don't Forget Too Much: Towards Machine Unlearning on Feature Levelcited by 11
  35. 2021SoK: Machine Learning Governancecited by 10
  36. 2023Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcarecited by 9
  37. 2025Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspectivecited by 9
  38. 2021Bayesian Inference Forgettingcited by 7

50 most cited of 95 All 95 (JSON)