# Post-Training Attribute Unlearning in Recommender Systems

arXiv: https://arxiv.org/abs/2403.06737 · HTML: https://mlsanity.com/paper/2403.06737/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2024.

## Built on by (most cited first, 24 of 24)

- [On Effects of Steering Latent Representation for Large Language Model Unlearning](https://mlsanity.com/paper/2408.06223/) (2024)
- [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)
- [A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions](https://mlsanity.com/paper/2412.12836/) (2024)
- [CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence](https://mlsanity.com/paper/2408.14393/) (2024)
- [Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraints](https://mlsanity.com/paper/2405.15328/) (2024)
- [Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization](https://mlsanity.com/paper/2603.27678/) (2026)
- [A Narrative Review on Large AI Models in Lung Cancer Screening, Diagnosis, and Treatment Planning](https://mlsanity.com/paper/2506.07236/) (2025)
- [Robust Anomaly Detection in Network Traffic: Evaluating Machine Learning Models on CICIDS2017](https://mlsanity.com/paper/2506.19877/) (2025)
- [FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks](https://mlsanity.com/paper/2601.22485/) (2026)
- [Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors](https://mlsanity.com/paper/2604.12359/) (2026)
- [Dual-Phase Playtime-guided Recommendation: Interest Intensity Exploration and Multimodal Random Walks](https://mlsanity.com/paper/2508.14058/) (2025)
- [Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness](https://mlsanity.com/paper/2505.10845/) (2025)
- [When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2602.00428/) (2026)
- [Time-TK: A Multi-Offset Temporal Interaction Framework Combining Transformer and Kolmogorov-Arnold Networks for Time Series Forecasting](https://mlsanity.com/paper/2602.11190/) (2026)
- [Distilling Transitional Pattern to Large Language Models for Multimodal Session-based Recommendation](https://mlsanity.com/paper/2504.10538/) (2025)
- [Customized Retrieval-Augmented Generation with LLM for Debiasing Recommendation Unlearning](https://mlsanity.com/paper/2511.05494/) (2025)
- [Fair Bayesian Data Selection via Generalized Discrepancy Measures](https://mlsanity.com/paper/2511.07032/) (2025)
- [Reproducibility Companion Paper: Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems](https://mlsanity.com/paper/2503.23032/) (2025)
- [Unlearning Algorithmic Biases over Graphs](https://mlsanity.com/paper/2505.14945/) (2025)
- [Beyond More Context: Retrieval Diversity Boosts Multi-Turn Intent Understanding](https://mlsanity.com/paper/2510.17940/) (2025)
- [LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems](https://mlsanity.com/paper/2510.20327/) (2025)
- [RaX-Crash: A Resource Efficient and Explainable Small Model Pipeline with an Application to City Scale Injury Severity Prediction](https://mlsanity.com/paper/2512.07848/) (2025)
- [The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails](https://mlsanity.com/paper/2608.01373/) (2026)
- [StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2609.38809/) (2026)

## Abstract (arXiv)

With the growing privacy concerns in recommender systems, recommendation unlearning is getting increasing attention. Existing studies predominantly use training data, i.e., model inputs, as unlearning target. However, attackers can extract private information from the model even if it has not been explicitly encountered during training. We name this unseen information as textitattribute and treat it as unlearning target. To protect the sensitive attribute of users, Attribute Unlearning (AU) aims to make target attributes indistinguishable. In this paper, we focus on a strict but practical setting of AU, namely Post-Training Attribute Unlearning (PoT-AU), where unlearning can only be performed after the training of the recommendation model is completed. To address the PoT-AU problem in recommender systems, we propose a two-component loss function. The first component is distinguishability loss, where we design a distribution-based measurement to make attribute labels indistinguishable from attackers. We further extend this measurement to handle multi-class attribute cases with efficient computational overhead. The second component is regularization loss, where we explore a function-space measurement that effectively maintains recommendation performance compared to parameter-space regularization. We use stochastic gradient descent algorithm to optimize our proposed loss. Extensive experiments on four real-world datasets demonstrate the effectiveness of our proposed methods.