mlsanityData to 7 Oct 2026

Machine Unlearning for Recommendation Systems: An Insight

arXiv 2401.10942 ↗First posted 17 Jan 2024cs.IR cs.AI cs.LGcited by 9

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

Abstract (arXiv)

This review explores machine unlearning (MUL) in recommendation systems, addressing adaptability, personalization, privacy, and bias challenges. Unlike traditional models, MUL dynamically adjusts system knowledge based on shifts in user preferences and ethical considerations. The paper critically examines MUL's basics, real-world applications, and challenges like algorithmic transparency. It sifts through literature, offering insights into how MUL could transform recommendations, discussing user trust, and suggesting paths for future research in responsible and user-focused artificial intelligence (AI). The document guides researchers through challenges involving the trade-off between personalization and privacy, encouraging contributions to meet practical demands for targeted data removal. Emphasizing MUL's role in secure and adaptive machine learning, the paper proposes ways to push its boundaries. The novelty of this paper lies in its exploration of the limitations of the methods, which highlights exciting prospects for advancing the field.

Key facts. Cited by 9 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 19 of its 30 references that are in the map. First posted on arXiv 17 Jan 2024.

Builds on

19 of 30 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems6 Oct
  2. 2023Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations13 Feb
  3. 2022Unlearning Protected User Attributes in Recommendations with Adversarial Training9 Jun
  4. 2022Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation22 Mar

Other references · 15

  1. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  2. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
  3. 2022Recommendation Unlearningcited by 71
  4. 2017Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Timecited by 46
  5. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
  6. 2022Federated Unlearning for On-Device Recommendationcited by 39
  7. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearningcited by 39
  8. 2022Unlearning Graph Classifiers with Limited Data Resourcescited by 31
  9. 2023Certified Minimax Unlearning with Generalization Rates and Deletion Capacitycited by 29
  10. 2023Selective and Collaborative Influence Function for Efficient Recommendation Unlearningcited by 25
  11. 2022Comprehensive Privacy Analysis on Federated Recommender System against Attribute Inference Attackscited by 21
  12. 2023Recommendation Unlearning via Influence Functioncited by 21
3 more
  1. 2023Distill to Delete: Unlearning in Graph Networks with Knowledge Distillationcited by 13
  2. 2022Forgetting Fast in Recommender Systemscited by 6
  3. 2023Recommendation Unlearning via Matrix Correctioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

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

9 papers.

  1. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  2. 2025BLUR: A Bi-Level Optimization Approach for LLM Unlearningcited by 23
  3. 2024Towards Efficient and Effective Unlearning of Large Language Models for Recommendationcited by 16
  4. 2024MEOW: MEMOry Supervised LLM Unlearning Via Inverted Factscited by 16
  5. 2024A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questionscited by 7
  6. 2025Deep Contrastive Unlearning for Language Modelscited by 4
  7. 2025Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearningcited by 3
  8. 2025Customized Retrieval-Augmented Generation with LLM for Debiasing Recommendation Unlearningcited by 1
  9. 2026Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearningcited by 1