# LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems

arXiv: https://arxiv.org/abs/2510.20327 · HTML: https://mlsanity.com/paper/2510.20327/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 24 of its 51 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 24 of 24)

- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning](https://mlsanity.com/paper/1805.04810/) (2018)
- [Graph Embedding for Recommendation against Attribute Inference Attacks](https://mlsanity.com/paper/2101.12549/) (2021)
- [Joint Item Recommendation and Attribute Inference: An Adaptive Graph Convolutional Network Approach](https://mlsanity.com/paper/2005.12021/) (2020)
- [Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation](https://mlsanity.com/paper/2203.11491/) (2022)
- [Selective and Collaborative Influence Function for Efficient Recommendation Unlearning](https://mlsanity.com/paper/2304.10199/) (2023)
- [Post-Training Attribute Unlearning in Recommender Systems](https://mlsanity.com/paper/2403.06737/) (2024)
- [Recommendation Unlearning via Influence Function](https://mlsanity.com/paper/2307.02147/) (2023)
- [Privacy-Aware Recommendation with Private-Attribute Protection using Adversarial Learning](https://mlsanity.com/paper/1911.09872/) (2019)
- [Unlearning Protected User Attributes in Recommendations with Adversarial Training](https://mlsanity.com/paper/2206.04500/) (2022)
- [Evaluating Supervised Learning Models for Fraud Detection: A Comparative Study of Classical and Deep Architectures on Imbalanced Transaction Data](https://mlsanity.com/paper/2505.22521/) (2025)
- [Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations](https://mlsanity.com/paper/2202.13295/) (2022)
- [KuaiSAR: A Unified Search And Recommendation Dataset](https://mlsanity.com/paper/2306.07705/) (2023)
- [Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems](https://mlsanity.com/paper/2310.05847/) (2023)
- [Gated Multimodal Graph Learning for Personalized Recommendation](https://mlsanity.com/paper/2506.00107/) (2025)
- [CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence](https://mlsanity.com/paper/2408.14393/) (2024)
- [Simultaneous Unlearning of Multiple Protected User Attributes From Variational Autoencoder Recommenders Using Adversarial Training](https://mlsanity.com/paper/2410.20965/) (2024)

## Abstract (arXiv)

With the growing demand for safeguarding sensitive user information in recommender systems, recommendation attribute unlearning is receiving increasing attention. Existing studies predominantly focus on single-attribute unlearning. However, privacy protection requirements in the real world often involve multiple sensitive attributes and are dynamic. Existing single-attribute unlearning methods cannot meet these real-world requirements due to i) CH1: the inability to handle multiple unlearning requests simultaneously, and ii) CH2: the lack of efficient adaptability to dynamic unlearning needs. To address these challenges, we propose LEGO, a lightweight and efficient multiple-attribute unlearning framework. Specifically, we divide the multiple-attribute unlearning process into two steps: i) Embedding Calibration removes information related to a specific attribute from user embedding, and ii) Flexible Combination combines these embeddings into a single embedding, protecting all sensitive attributes. We frame the unlearning process as a mutual information minimization problem, providing LEGO a theoretical guarantee of simultaneous unlearning, thereby addressing CH1. With the two-step framework, where Embedding Calibration can be performed in parallel and Flexible Combination is flexible and efficient, we address CH2. Extensive experiments on three real-world datasets across three representative recommendation models demonstrate the effectiveness and efficiency of our proposed framework. Our code and appendix are available at https://github.com/anonymifish/lego-rec-multiple-attribute-unlearning.