mlsanityData to 7 Oct 2026

FUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary Unlearning

arXiv 2501.16614 ↗First posted 28 Jan 2025cs.LGcited by 7

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Machine unlearning is an emerging field that selectively removes specific data samples from a trained model. This capability is crucial for addressing privacy concerns, complying with data protection regulations, and correcting errors or biases introduced by certain data. Unlike traditional machine learning, where models are typically static once trained, machine unlearning facilitates dynamic updates that enable the model to ``forget'' information without requiring complete retraining from scratch. There are various machine unlearning methods, some of which are more time-efficient when data removal requests are fewer. To decrease the execution time of such machine unlearning methods, we aim to reduce the size of data removal requests based on the fundamental assumption that the removal of certain data would not result in a distinguishable retrained model. We first propose the concept of unnecessary unlearning, which indicates that the model would not alter noticeably after removing some data points. Subsequently, we review existing solutions that can be used to solve our problem. We highlight their limitations in adaptability to different unlearning scenarios and their reliance on manually selected parameters. We consequently put forward FUNU, a method to identify data points that lead to unnecessary unlearning. FUNU circumvents the limitations of existing solutions. The idea is to discover data points within the removal requests that have similar neighbors in the remaining dataset. We utilize a reference model to set parameters for finding neighbors, inspired from the area of model memorization. We provide a theoretical analysis of the privacy guarantee offered by FUNU and conduct extensive experiments to validate its efficacy.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 27 of its 49 references that are in the map. First posted on arXiv 28 Jan 2025.

Builds on

27 of 49 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Machine Unlearning: A Survey6 Jun
  2. 2022Deep Unlearning via Randomized Conditionally Independent Hessians15 Apr
  3. 2021Remember What You Want to Forget: Algorithms for Machine Unlearning4 Mar

Other references · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019Machine Unlearningcited by 1,020
  3. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  4. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  5. 2019Certified Data Removal from Machine Learning Modelscited by 512
  6. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 492
  7. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 452
  8. 2018Not All Samples Are Created Equal: Deep Learning with Importance Samplingcited by 323
  9. 2020Amnesiac Machine Learningcited by 305
  10. 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 259
  11. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  12. 2018Representer Point Selection for Explaining Deep Neural Networkscited by 187
12 more
  1. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 171
  2. 2020Mixed-Privacy Forgetting in Deep Networkscited by 158
  3. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 143
  4. 2021Graph Unlearningcited by 129
  5. 2022The Privacy Onion Effect: Memorization is Relativecited by 128
  6. 2020Estimating Example Difficulty Using Variance of Gradientscited by 96
  7. 2023GIF: A General Graph Unlearning Strategy via Influence Functioncited by 59
  8. 2019Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applicationscited by 43
  9. 2022Characterizing Datapoints via Second-Split Forgettingcited by 37
  10. 2024Membership Inference Attacks and Defenses in Federated Learning: A Surveycited by 27
  11. 2023Memorization Through the Lens of Curvature of Loss Function Around Samplescited by 24
  12. 2024Unveiling Privacy, Memorization, and Input Curvature Linkscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMscited by 41
  2. 2025OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Modelscited by 9
  3. 2025Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacycited by 4
  4. 2025Sharpness-Aware Parameter Selection for Machine Unlearningcited by 2
  5. 2025When unlearning is free: leveraging low influence points to reduce computational costscited by 0
  6. 2026Machine Unlearning in Low-Dimensional Feature Subspacecited by 0
  7. 2026Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forgetcited by 0