{"ID":2851054,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.20327","arxiv_id":"2510.20327","title":"LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems","abstract":"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.","short_abstract":"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 sensit...","url_abs":"https://arxiv.org/abs/2510.20327","url_pdf":"https://arxiv.org/pdf/2510.20327v1","authors":"[\"Fengyuan Yu\",\"Yuyuan Li\",\"Xiaohua Feng\",\"Junjie Fang\",\"Tao Wang\",\"Chaochao Chen\"]","published":"2025-10-23T08:20:47Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":607863,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2851054,"paper_url":"https://arxiv.org/abs/2510.20327","paper_title":"LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems","repo_url":"https://github.com/anonymifish/lego-rec-multiple-attribute-unlearning","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}