mlsanityData to 14 Oct 2026

Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks

arXiv 1911.04933 ↗First posted 12 Nov 2019cs.LG stat.MLcited by 618

Not on the map. Why?

Cited by 509 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We explore the problem of selectively forgetting a particular subset of the data used for training a deep neural network. While the effects of the data to be forgotten can be hidden from the output of the network, insights may still be gleaned by probing deep into its weights. We propose a method for "scrubbing'" the weights clean of information about a particular set of training data. The method does not require retraining from scratch, nor access to the data originally used for training. Instead, the weights are modified so that any probing function of the weights is indistinguishable from the same function applied to the weights of a network trained without the data to be forgotten. This condition is a generalized and weaker form of Differential Privacy. Exploiting ideas related to the stability of stochastic gradient descent, we introduce an upper-bound on the amount of information remaining in the weights, which can be estimated efficiently even for deep neural networks.

Key facts. Cited by 618 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 44; 2023: 72; 2024: 176; 2025: 164; 2026: 143.

618 papers.

Sort:

By area:

  1. 2022Editing Models with Task Arithmeticcited by 1,120
  2. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  3. 2023Erasing Concepts from Diffusion Modelscited by 539
  4. 2024TOFU: A Task of Fictitious Unlearning for LLMscited by 533
  5. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearningcited by 504
  6. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Modelscited by 437
  7. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 386
  8. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 371
  9. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 317
  10. 2022A Survey of Machine Unlearningcited by 312
  11. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearningcited by 279
  12. 2023Towards Unbounded Machine Unlearningcited by 268
38 more
  1. 2024MUSE: Machine Unlearning Six-Way Evaluation for Language Modelscited by 261
  2. 2024Rethinking Machine Unlearning for Large Language Modelscited by 257
  3. 2021Machine Unlearning of Features and Labelscited by 229
  4. 2023In-Context Unlearning: Language Models as Few Shot Unlearnerscited by 224
  5. 2021Fast Yet Effective Machine Unlearningcited by 217
  6. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMscited by 215
  7. 2023Model Sparsity Can Simplify Machine Unlearningcited by 214
  8. 2023To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Nowcited by 210
  9. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teachercited by 194
  10. 2023Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampeningcited by 181
  11. 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Modelscited by 177
  12. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 171
  13. 2021Graph Unlearningcited by 138
  14. 2024Tamper-Resistant Safeguards for Open-Weight LLMscited by 138
  15. 2023Boundary Unlearningcited by 134
  16. 2022Zero-Shot Machine Unlearningcited by 133
  17. 2022Continual Learning and Private Unlearningcited by 130
  18. 2024Machine Unlearning of Pre-trained Large Language Modelscited by 119
  19. 2022Measuring Forgetting of Memorized Training Examplescited by 118
  20. 2021Federated Unlearning via Class-Discriminative Pruningcited by 115
  21. 2024SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearningcited by 104
  22. 2023KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignmentcited by 99
  23. 2024Guardrail Baselines for Unlearning in LLMscited by 96
  24. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?cited by 95
  25. 2023Machine Unlearning: Solutions and Challengescited by 93
  26. 2024What makes unlearning hard and what to do about itcited by 89
  27. 2024Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Differencecited by 88
  28. 2023Circumventing Concept Erasure Methods For Text-to-Image Generative Modelscited by 85
  29. 2022Towards Adversarial Evaluations for Inexact Machine Unlearningcited by 84
  30. 2022Deep Unlearning via Randomized Conditionally Independent Hessianscited by 84
  31. 2024Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearningcited by 84
  32. 2024Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacycited by 82
  33. 2022Recommendation Unlearningcited by 80
  34. 2024RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Modelscited by 78
  35. 2024LLM Unlearning via Loss Adjustment with Only Forget Datacited by 75
  36. 2024Do Unlearning Methods Remove Information from Language Model Weights?cited by 73
  37. 2023Fast Model Debias with Machine Unlearningcited by 72
  38. 2025wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Modelscited by 71

50 most cited of 618 All 618 (JSON)