mlsanityData to 7 Oct 2026

Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation

arXiv 2203.11491 ↗First posted 22 Mar 2022cs.IR cs.LGcited by 27

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

Abstract (arXiv)

Privacy laws and regulations enforce data-driven systems, e.g., recommender systems, to erase the data that concern individuals. As machine learning models potentially memorize the training data, data erasure should also unlearn the data lineage in models, which raises increasing interest in the problem of Machine Unlearning (MU). However, existing MU methods cannot be directly applied into recommendation. The basic idea of most recommender systems is collaborative filtering, but existing MU methods ignore the collaborative information across users and items. In this paper, we propose a general erasable recommendation framework, namely LASER, which consists of Group module and SeqTrain module. Firstly, Group module partitions users into balanced groups based on their similarity of collaborative embedding learned via hypergraph. Then SeqTrain module trains the model sequentially on all groups with curriculum learning. Both theoretical analysis and experiments on two real-world datasets demonstrate that LASER can not only achieve efficient unlearning, but also outperform the state-of-the-art unlearning framework in terms of model utility.

Key facts. Cited by 27 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 55 references that are in the map. First posted on arXiv 22 Mar 2022.

Builds on

19 of 55 references.

References · 19

  1. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  2. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  3. 2017Neural Collaborative Filteringcited by 1,108
  4. 2019Machine Unlearningcited by 1,020
  5. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 517
  6. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  7. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
  8. 2020Amnesiac Machine Learningcited by 305
  9. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 285
  10. 2019On the Accuracy of Influence Functions for Measuring Group Effectscited by 146
  11. 2021Graph Unlearningcited by 129
  12. 2020Neural Collaborative Filtering vs. Matrix Factorization Revisitedcited by 123
7 more
  1. 2016Higher-order organization of complex networkscited by 109
  2. 2020Machine Unlearning: Linear Filtration for Logit-based Classifierscited by 89
  3. 2016Data Poisoning Attacks on Factorization-Based Collaborative Filteringcited by 78
  4. 2022Recommendation Unlearningcited by 71
  5. 2022PUMA: Performance Unchanged Model Augmentation for Training Data Removalcited by 56
  6. 2019Random Walks on Hypergraphs with Edge-Dependent Vertex Weightscited by 45
  7. 2021Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectivescited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 9; 2024: 10; 2025: 6; 2026: 1.

27 papers.

Sort:

By area:

  1. 2024MUSE: Machine Unlearning Six-Way Evaluation for Language Modelscited by 251
  2. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  3. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  4. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
  5. 2024A Review on Machine Unlearningcited by 30
  6. 2023MultiDelete for Multimodal Machine Unlearningcited by 20
  7. 2023Machine Unlearning: A Surveycited by 18
  8. 2024Towards Efficient and Effective Unlearning of Large Language Models for Recommendationcited by 16
  9. 2024MEOW: MEMOry Supervised LLM Unlearning Via Inverted Factscited by 16
  10. 2023Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systemscited by 15
  11. 2025Exact Unlearning of Finetuning Data via Model Merging at Scalecited by 14
  12. 2023Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendationscited by 12
15 more
  1. 2025BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlapcited by 12
  2. 2024Machine Unlearning for Recommendation Systems: An Insightcited by 9
  3. 2024A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questionscited by 7
  4. 2023Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generationcited by 6
  5. 2023Recommendation Unlearning via Matrix Correctioncited by 6
  6. 2024Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraintscited by 5
  7. 2024Controllable Unlearning for Image-to-Image Generative Models via varepsilon-Constrained Optimizationcited by 5
  8. 2023On the Effectiveness of Unlearning in Session-Based Recommendationcited by 4
  9. 2024Privacy in LLM-based Recommendation: Recent Advances and Future Directionscited by 2
  10. 2025Membership Inference Attacks on Recommender System: A Surveycited by 2
  11. 2025Customized Retrieval-Augmented Generation with LLM for Debiasing Recommendation Unlearningcited by 1
  12. 2026U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendationcited by 1
  13. 2022Recommendation with User Active Disclosing Willingnesscited by 0
  14. 2025Pre-training for Recommendation Unlearningcited by 0
  15. 2025LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systemscited by 0