mlsanityData to 7 Oct 2026

Machine Unlearning Method Based On Projection Residual

arXiv 2209.15276 ↗First posted 30 Sep 2022cs.LG cs.AIcited by 4

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Machine learning models (mainly neural networks) are used more and more in real life. Users feed their data to the model for training. But these processes are often one-way. Once trained, the model remembers the data. Even when data is removed from the dataset, the effects of these data persist in the model. With more and more laws and regulations around the world protecting data privacy, it becomes even more important to make models forget this data completely through machine unlearning. This paper adopts the projection residual method based on Newton iteration method. The main purpose is to implement machine unlearning tasks in the context of linear regression models and neural network models. This method mainly uses the iterative weighting method to completely forget the data and its corresponding influence, and its computational cost is linear in the feature dimension of the data. This method can improve the current machine learning method. At the same time, it is independent of the size of the training set. Results were evaluated by feature injection testing (FIT). Experiments show that this method is more thorough in deleting data, which is close to model retraining.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 24 of its 41 references that are in the map. First posted on arXiv 30 Sep 2022.

Builds on

24 of 41 references.

Closest ancestors · 3

Same direction, newest first

  1. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning22 Oct
  2. 2021Adaptive Machine Unlearning8 Jun
  3. 2021Remember What You Want to Forget: Algorithms for Machine Unlearning4 Mar

Other references · 21

  1. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,829
  4. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  5. 2019Machine Unlearningcited by 1,020
  6. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
  7. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 597
  8. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 565
  9. 2019Certified Data Removal from Machine Learning Modelscited by 512
  10. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  11. 2020Amnesiac Machine Learningcited by 305
  12. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
9 more
  1. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  2. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  3. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 171
  4. 2020Mixed-Privacy Forgetting in Deep Networkscited by 158
  5. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 143
  6. 2020Machine Unlearning: Linear Filtration for Logit-based Classifierscited by 89
  7. 2020Coded Machine Unlearningcited by 35
  8. 2020SECure: A Social and Environmental Certificate for AI Systemscited by 7
  9. 2018Quantized Compressive K-Meanscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 1; 2026: 1.

4 papers.

  1. 2023Fast Model Debias with Machine Unlearningcited by 70
  2. 2023Machine Unlearning Methodology base on Stochastic Teacher Networkcited by 1
  3. 2025UNO: Unlearning via Orthogonalization in Generative modelscited by 0
  4. 2026Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillationcited by 0