mlsanityData to 7 Oct 2026

Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations

arXiv 2302.06676 ↗First posted 13 Feb 2023cs.LG cs.IRcited by 12

On the map: LLM safety and security → Membership inference attacks

Abstract (arXiv)

People break up, miscarry, and lose loved ones. Their online streaming and shopping recommendations, however, do not necessarily update, and may serve as unhappy reminders of their loss. When users want to renege on their past actions, they expect the recommender platforms to erase selective data at the model level. Ideally, given any specified user history, the recommender can unwind or "forget", as if the record was not part of training. To that end, this paper focuses on simple but widely deployed bi-linear models for recommendations based on matrix completion. Without incurring the cost of re-training, and without degrading the model unnecessarily, we develop Unlearn-ALS by making a few key modifications to the fine-tuning procedure under Alternating Least Squares optimisation, thus applicable to any bi-linear models regardless of the training procedure. We show that Unlearn-ALS is consistent with retraining without any model degradation and exhibits rapid convergence, making it suitable for a large class of existing recommenders.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 23 of its 59 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

23 of 59 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation22 Mar
  2. 2021Membership Inference Attacks From First Principles7 Dec
  3. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov

Other references · 20

  1. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  2. 2019Machine Unlearningcited by 1,020
  3. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  4. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  5. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  6. 2020Label-Only Membership Inference Attackscited by 371
  7. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
  8. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  9. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  10. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  11. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  12. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 164
8 more
  1. 2017How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utilitycited by 116
  2. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 108
  3. 2017Fast Matrix Factorization for Online Recommendation with Implicit Feedbackcited by 100
  4. 2020Feedback Loop and Bias Amplification in Recommender Systemscited by 89
  5. 2022Recommendation Unlearningcited by 71
  6. 2019Degenerate Feedback Loops in Recommender Systemscited by 67
  7. 2015Fast Differentially Private Matrix Factorizationcited by 20
  8. 2020Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queriescited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 2; 2026: 1.

12 papers.

  1. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  2. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  3. 2025BLUR: A Bi-Level Optimization Approach for LLM Unlearningcited by 23
  4. 2024Towards Efficient and Effective Unlearning of Large Language Models for Recommendationcited by 16
  5. 2024MEOW: MEMOry Supervised LLM Unlearning Via Inverted Factscited by 16
  6. 2023A Survey of Graph Unlearningcited by 12
  7. 2024Machine Unlearning for Recommendation Systems: An Insightcited by 9
  8. 2024A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questionscited by 7
  9. 2023Recommendation Unlearning via Matrix Correctioncited by 6
  10. 2023On the Effectiveness of Unlearning in Session-Based Recommendationcited by 4
  11. 2025Customized Retrieval-Augmented Generation with LLM for Debiasing Recommendation Unlearningcited by 1
  12. 2026Obliviate: Efficient Unlearning in Recommender Systemscited by 0