{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T02:24:13Z","timestamp":1758248653100,"version":"3.44.0"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"DOI":"10.13039\/100016804","name":"Shenzhen Natural Science Foundation","doi-asserted-by":"crossref","award":["JCYJ20240813141441054"],"award-info":[{"award-number":["JCYJ20240813141441054"]}],"id":[{"id":"10.13039\/100016804","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62461160311 and 62272315"],"award-info":[{"award-number":["62461160311 and 62272315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2023YFF0725100"],"award-info":[{"award-number":["2023YFF0725100"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2025,10,31]]},"abstract":"<jats:p>Cross-user federated recommendation (CUFR) is a promising solution for providing personalized services without collecting users\u2019 raw data. However, most previous CUFR works mainly focus on providing accurate and privacy-preserving personalized recommendations, but overlook the fact that users can opt out at any time during the training process. In response, we study an emerging and new problem of efficiently training an unlearned model to forget the data of the clients who leave a federated system. It is challenging to simply apply or slightly modify existing machine unlearning or federated unlearning methods to CUFR because of the unique collaboration effect in recommender systems. Although a recent gradient calibration-based method (i.e., FRU) shows promising in training an unlearned model, there are still some limitations: (i) there is a potential possibility that some clients run out of the storage space, (ii) all the remaining clients need to participate in computing the new gradients, (iii) it masks the uniqueness of the local gradients, and (iv) the errors of the calibrated gradients will increase gradually with more iterations. In this article, we propose a novel CUFR unlearning (CUFRU) method. Specifically, we design a gradient transfer station (GTS) module for storing the historical gradients while enabling clients to dynamically participate in the computation of the calibrated gradients with the new gradients based on their online status. Moreover, we design a novel iteration-aware gradient calibration mechanism to strike a balance between the weights of the historical and new gradients at the different stages of the unlearning process, alleviating the calibration errors. Finally, we conduct extensive experiments on three real-world datasets to show that our CUFRU can more efficiently train an unlearned model with the competitive recommendation performance.<\/jats:p>","DOI":"10.1145\/3749990","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T17:13:10Z","timestamp":1753377190000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-User Federated Recommendation Unlearning"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7830-6968","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0522-2654","authenticated-orcid":false,"given":"Enyue","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6326-9531","authenticated-orcid":false,"given":"Weike","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5059-8360","authenticated-orcid":false,"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Academy for Artificial Intelligence, Hong Kong Polytechnic University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6933-5760","authenticated-orcid":false,"given":"Zhong","family":"Ming","sequence":"additional","affiliation":[{"name":"College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2025,9,18]]},"reference":[{"key":"e_1_3_2_1_2","unstructured":"Muhammad Ammad-Ud-Din Elena Ivannikova Suleiman A. Khan Were Oyomno Qiang Fu Kuan Eeik Tan and Adrian Flanagan. 2019. Federated collaborative filtering for privacy-preserving personalized recommendation system. arXiv:1901.09888. Retrieved from https:\/\/arxiv.org\/abs\/1901.09888"},{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00019"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3501812"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511997"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3559352"},{"key":"e_1_3_2_6_2","first-page":"14516","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems (NeuIPS \u201923)","author":"Chen Ruizhe","year":"2024","unstructured":"Ruizhe Chen, Jianfei Yang, Huimin Xiong, Jianhong Bai, Tianxiang Hu, Jin Hao, Yang Feng, Joey Tianyi Zhou, Jian Wu, and Zuozhu Liu. 2024. Fast model debias with machine unlearning. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NeuIPS \u201923), 14516\u201314539."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706633"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17371"},{"key":"e_1_3_2_9_2","unstructured":"Hanlin Gu Gongxi Zhu Jie Zhang Xinyuan Zhao Yuxing Han Lixin Fan and Qiang Yang. 2024. Unlearning during learning: An efficient federated machine unlearning method. arXiv:2405.15474. Retrieved from https:\/\/arxiv.org\/abs\/2405.15474"},{"key":"e_1_3_2_10_2","unstructured":"Chuan Guo Tom Goldstein Awni Hannun and Laurens Van Der Maaten. 2019. Certified data removal from machine learning models. arXiv:1911.03030. Retrieved from https:\/\/arxiv.org\/abs\/1911.03030"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645626"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103996"},{"key":"e_1_3_2_14_2","unstructured":"Zhiyu Hu Yang Zhang Minghao Xiao Wenjie Wang Fuli Feng and Xiangnan He. 2024. Exact and efficient unlearning for large language model-based recommendation. arXiv:2404.10327. Retrieved from https:\/\/arxiv.org\/abs\/2404.10327"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706419"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Yasser H. Khalil Leo Brunswic Soufiane Lamghari Xu Li Mahdi Beitollahi and Xi Chen. 2025. NoT: Federated unlearning via weight negation. arXiv:2503.05657. Retrieved from https:\/\/arxiv.org\/abs\/2503.05657","DOI":"10.1109\/CVPR52734.2025.02399"},{"key":"e_1_3_2_17_2","unstructured":"Jakub Konecn\u1ef3 H. Brendan McMahan Felix X. Yu Peter Richt\u00e1rik Ananda Theertha Suresh and Dave Bacon. 2016. Federated learning: Strategies for improving communication efficiency. arXiv:1610.05492. Retrieved from https:\/\/arxiv.org\/abs\/1610.05492"},{"key":"e_1_3_2_18_2","first-page":"1957","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems (NeuIPS \u201923)","author":"Kurmanji Meghdad","year":"2023","unstructured":"Meghdad Kurmanji, Peter Triantafillou, Jamie Hayes, and Eleni Triantafillou. 2023. Towards unbounded machine unlearning. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NeuIPS \u201923), 1957\u20131987."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657763"},{"key":"e_1_3_2_20_2","first-page":"12611","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems (NeuIPS \u201923)","author":"Li Yuyuan","year":"2023","unstructured":"Yuyuan Li, Chaochao Chen, Yizhao Zhang, Weiming Liu, Lingjuan Lyu, Xiaolin Zheng, Dan Meng, and Wang Jun. 2023. UltraRe: Enhancing RecEraser for recommendation unlearning via error decomposition. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NeuIPS \u201923), 12611\u201312625."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111124"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3363505"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16546"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3548456"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521274"},{"key":"e_1_3_2_26_2","first-page":"51584","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems (NeuIPS \u201923)","author":"Liu Jiancheng","year":"2023","unstructured":"Jiancheng Liu, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, P. R. A. N. A. Y. Sharma, Sijia Liu, et al. 2023. Model sparsity can simplify machine unlearning. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NeuIPS \u201923), 51584\u201351605."},{"key":"e_1_3_2_27_2","unstructured":"Sijia Liu Yuanshun Yao Jinghan Jia Stephen Casper Nathalie Baracaldo Peter Hase Xiaojun Xu Yuguang Yao Hang Li Kush R. Varshney et al. 2024. Rethinking machine unlearning for large language models. arXiv:2402.08787. Retrieved from https:\/\/arxiv.org\/abs\/2402.08787"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/245"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29321"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3194884"},{"key":"e_1_3_2_31_2","first-page":"1273","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (PMLR \u201917)","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (PMLR \u201917), 1273\u20131282."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645702"},{"key":"e_1_3_2_33_2","first-page":"2691","volume-title":"Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI \u201913)","author":"Pan Weike","year":"2013","unstructured":"Weike Pan and Li Chen. 2013. GBPR: Group preference based Bayesian personalized ranking for one-class collaborative filtering. In Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI \u201913), 2691\u20132697."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i19.34181"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108441"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13677-023-00435-5"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608781"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266233"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30714-9"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539119"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635823"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3603620"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13081589"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4310-7"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645492"},{"key":"e_1_3_2_46_2","unstructured":"Wei Yuan Chaoqun Yang Liang Qu Quoc Viet Hung Nguyen Guanhua Ye and Hongzhi Yin. 2024. PTF-FSR: A parameter transmission-free federated sequential recommender system. arXiv:2406.05387. Retrieved from https:\/\/arxiv.org\/abs\/2406.05387"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570463"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.3034770"},{"key":"e_1_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Chunxu Zhang Guodong Long Tianyi Zhou Peng Yan Zijian Zhang Chengqi Zhang and Bo Yang. 2023. Dual personalization on federated recommendation. arXiv:2301.08143. Retrieved from https:\/\/arxiv.org\/abs\/2301.08143","DOI":"10.24963\/ijcai.2023\/507"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645525"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611978032.62"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3297905"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498386"},{"key":"e_1_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Zhengyi Zhong Weidong Bao Ji Wang Shuai Zhang Jingxuan Zhou Lingjuan Lyu and Wei Yang Bryan Lim. 2025. Unlearning through knowledge overwriting: Reversible federated unlearning via selective sparse adapter. arXiv:2502.20709. Retrieved from https:\/\/arxiv.org\/abs\/2502.20709","DOI":"10.1109\/CVPR52734.2025.02855"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583305"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3749990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T17:03:35Z","timestamp":1758215015000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3749990"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,18]]},"references-count":55,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10,31]]}},"alternative-id":["10.1145\/3749990"],"URL":"https:\/\/doi.org\/10.1145\/3749990","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"type":"print","value":"2157-6904"},{"type":"electronic","value":"2157-6912"}],"subject":[],"published":{"date-parts":[[2025,9,18]]},"assertion":[{"value":"2025-01-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}