# Simultaneous Unlearning of Multiple Protected User Attributes From Variational Autoencoder Recommenders Using Adversarial Training

arXiv: https://arxiv.org/abs/2410.20965 · HTML: https://mlsanity.com/paper/2410.20965/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 28 Oct 2024.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [A Survey on the Fairness of Recommender Systems](https://mlsanity.com/paper/2206.03761/) (2022)
- [Personalized Counterfactual Fairness in Recommendation](https://mlsanity.com/paper/2105.09829/) (2021)
- [Parameter-efficient Modularised Bias Mitigation via AdapterFusion](https://mlsanity.com/paper/2302.06321/) (2023)
- [Trustworthy Recommender Systems](https://mlsanity.com/paper/2208.06265/) (2022)
- [Unlearning Protected User Attributes in Recommendations with Adversarial Training](https://mlsanity.com/paper/2206.04500/) (2022)
- [Privacy in Social Media: Identification, Mitigation and Applications](https://mlsanity.com/paper/1808.02191/) (2018)
- [Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks](https://mlsanity.com/paper/2205.15171/) (2022)
- [Debiasing Learning for Membership Inference Attacks Against Recommender Systems](https://mlsanity.com/paper/2206.12401/) (2022)

## Built on by (most cited first, 3 of 3)

- [A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions](https://mlsanity.com/paper/2412.12836/) (2024)
- [RAID: An In-Training Defense against Attribute Inference Attacks in Recommender Systems](https://mlsanity.com/paper/2504.11510/) (2025)
- [LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems](https://mlsanity.com/paper/2510.20327/) (2025)

## Abstract (arXiv)

In widely used neural network-based collaborative filtering models, users' history logs are encoded into latent embeddings that represent the users' preferences. In this setting, the models are capable of mapping users' protected attributes (e.g., gender or ethnicity) from these user embeddings even without explicit access to them, resulting in models that may treat specific demographic user groups unfairly and raise privacy issues. While prior work has approached the removal of a single protected attribute of a user at a time, multiple attributes might come into play in real-world scenarios. In the work at hand, we present AdvXMultVAE which aims to unlearn multiple protected attributes (exemplified by gender and age) simultaneously to improve fairness across demographic user groups. For this purpose, we couple a variational autoencoder (VAE) architecture with adversarial training (AdvMultVAE) to support simultaneous removal of the users' protected attributes with continuous and/or categorical values. Our experiments on two datasets, LFM-2b-100k and Ml-1m, from the music and movie domains, respectively, show that our approach can yield better results than its singular removal counterparts (based on AdvMultVAE) in effectively mitigating demographic biases whilst improving the anonymity of latent embeddings.