{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T08:45:56Z","timestamp":1776415556600,"version":"3.51.2"},"reference-count":42,"publisher":"Wiley","issue":"25-26","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3321504"],"award-info":[{"award-number":["2023YFC3321504"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Federated learning (FL) enables collaborative model training across multiple parties while preserving data privacy. However, FL remains vulnerable to privacy leakage through model updates. Differential privacy (DP) has been incorporated into FL by adding noise to model updates to ensure robust privacy protections. Traditional DP methods set a fixed sensitivity limit, resulting in excessive noise addition and performance degradation, especially in complex models such as RS, where the high\u2010dimensional parameters of the model pose a major challenge to effective noise addition. The higher the parameter dimension of the model, the greater the effect of including all the noise will be on the performance of the recommendation system. This study presents an adaptive local differential privacy technique grounded in Fisher information for reinforcement learning, which dynamically modifies the privacy budget by assessing the significance of model parameters during each training iteration. Specifically, Fisher information is used to assess the significance of each parameter layer, with more noise added to less important layers and less noise added to more critical layers. This approach optimizes the noise allocation while maintaining model performance under the DP guarantee. At the same time, we decouple the federated recommendation system (FRS) from the DP mechanism, enabling seamless integration with a variety of recommendation models. We assess the effectiveness of the proposed method through theoretical analysis and experiments on multiple benchmark datasets. The results demonstrate that the Fisher\u2010based adaptive DP method significantly improves model performance compared to traditional fixed\u2010sensitivity DP methods in FL environments, particularly addressing the challenges posed by the complexity of RS parameters.<\/jats:p>","DOI":"10.1002\/cpe.70334","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T04:52:31Z","timestamp":1760417551000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Local Differential Privacy Method With Layer\u2010Wise Importance Based on Fisher Information in Federated Recommendation Systems"],"prefix":"10.1002","volume":"37","author":[{"given":"Jieyi","family":"Yan","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering Shandong University  Qingdao China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9925-303X","authenticated-orcid":false,"given":"Chao","family":"Zhai","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering Shandong University  Qingdao China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lina","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering Shandong University  Qingdao China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aniket","family":"Mahanti","sequence":"additional","affiliation":[{"name":"School of Computer Science University of Auckland  Auckland New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongqiao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering Shandong University  Qingdao China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yawen","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering Shandong University  Qingdao China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13106201"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10207-023-00710-1"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652891"},{"issue":"9","key":"e_1_2_10_5_1","first-page":"11729","article-title":"A Survey on Federated Recommendation Systems","volume":"35","author":"Sun Z.","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"9","key":"e_1_2_10_6_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3656165","article-title":"Horizontal Federated Recommender System: A Survey","volume":"56","author":"Wang L.","year":"2024","journal-title":"ACM Computing Surveys"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-022-03644-w"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-023-00442-4"},{"issue":"4","key":"e_1_2_10_9_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3501815","article-title":"Federated Social Recommendation With Graph Neural Network","volume":"13","author":"Liu Z.","year":"2022","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"issue":"4","key":"e_1_2_10_10_1","first-page":"1","article-title":"LightFR: Lightweight Federated Recommendation With Privacy\u2010Preserving Matrix Factorization","volume":"41","author":"Zhang H.","year":"2023","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","unstructured":"C.Wu F.Wu Y.Cao Y.Huang andX.Xie \u201cFedGNN: Federated Graph Neural Network for Privacy\u2010Preserving Recommendation \u201darXiv Preprint arXiv:2102.04925 (2021).","DOI":"10.1038\/s41467-022-30714-9"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3151670"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2025.3528235"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3533090"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128653"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102796"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.06.028"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103852"},{"key":"e_1_2_10_19_1","unstructured":"M.Ammad\u2010Ud\u2010Din E.Ivannikova S. A.Khan et al. \u201cFederated Collaborative Filtering for Privacy\u2010Preserving Personalized Recommendation System \u201darXiv Preprint arXiv:1901.09888 (2019)."},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106946"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6233"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3185327"},{"issue":"4","key":"e_1_2_10_23_1","first-page":"944","article-title":"Secure and Privacy\u2010Preserving Decentralized Federated Learning for Personalized Recommendations in Consumer Electronics Using Blockchain and Homomorphic Encryption","volume":"69","author":"Gupta B. B.","year":"2023","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.12.024"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3295894"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119728"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599889"},{"key":"e_1_2_10_28_1","first-page":"760","volume-title":"Uncertainty in Artificial Intelligence","author":"Hannun A.","year":"2021"},{"key":"e_1_2_10_29_1","first-page":"1612","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Jhunjhunwala D.","year":"2024"},{"key":"e_1_2_10_30_1","unstructured":"G. M.vanderVen \u201cOn the Computation of the Fisher Information in Continual Learning \u201darXiv Preprint arXiv:2502.11756 (2025)."},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29632"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10825241"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_2_10_34_1","unstructured":"J.Fu Y.Hong X.Ling et al. \u201cDifferentially Private Federated Learning: A Systematic Review \u201darXiv Preprint arXiv:2405.08299 (2024)."},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12454"},{"key":"e_1_2_10_36_1","first-page":"72181","article-title":"Dynamic Personalized Federated Learning With Adaptive Differential Privacy","volume":"36","author":"Yang X.","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"e_1_2_10_38_1","unstructured":"Y.Inc \u201cYelp Open Dataset \u201d(2023)."},{"key":"e_1_2_10_39_1","volume-title":"Music Recommendation and Discovery in the Long Tail","author":"Celma Herrada \u00d2.","year":"2009"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3438872.3439097"},{"key":"e_1_2_10_41_1","first-page":"89111","article-title":"Have It Your Way: Individualized Privacy Assignment for DP\u2010SGD","volume":"37","author":"Boenisch F.","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_42_1","first-page":"15276","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Tang Q.","year":"2024"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108441"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T09:03:49Z","timestamp":1762938229000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70334"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":42,"journal-issue":{"issue":"25-26","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1002\/cpe.70334"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70334","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"2025-02-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70334"}}