{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:10:07Z","timestamp":1789085407416,"version":"build-2803163510"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:00:00Z","timestamp":1780876800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.neunet.2026.109231","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:35:40Z","timestamp":1780727740000},"page":"109231","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Margin-aware prototype learning for client withdrawal in federated unlearning"],"prefix":"10.1016","volume":"204","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6692-292X","authenticated-orcid":false,"given":"Yixuan","family":"Qiu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6232-0040","authenticated-orcid":false,"given":"Shaofei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2379-6104","authenticated-orcid":false,"given":"Chenhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weitong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109231_bib0001","series-title":"2024 20th international conference on mobility, sensing and networking (MSN)","article-title":"Lightweight federated unlearning for iot sensing systems","author":"Ameen","year":"2024"},{"issue":"5","key":"10.1016\/j.neunet.2026.109231_bib0002","first-page":"921","article-title":"Speed up federated unlearning with temporary local models","volume":"10","author":"Ameen","year":"2025","journal-title":"IEEE Transactions on Sustainable Computing"},{"key":"10.1016\/j.neunet.2026.109231_bib0003","series-title":"NeurIPS","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","author":"Blanchard","year":"2017"},{"key":"10.1016\/j.neunet.2026.109231_bib0004","series-title":"Sp","article-title":"Machine unlearning","author":"Bourtoule","year":"2021"},{"key":"10.1016\/j.neunet.2026.109231_bib0005","first-page":"499","article-title":"Stability and generalization","volume":"2","author":"Bousquet","year":"2002","journal-title":"JMLR"},{"key":"10.1016\/j.neunet.2026.109231_bib0006","unstructured":"Caldas, S., Duddu, S. M. K., Wu, P., Li, T., Kone\u010dn\u00fd, J., McMahan, H. B., Smith, V., & Talwalkar, A. (2018). LEAF: A benchmark for federated settings. arXiv preprint arXiv: 1812.01097."},{"key":"10.1016\/j.neunet.2026.109231_bib0007","series-title":"Sp","article-title":"FedRecover: Recovering from poisoning attacks in federated learning using historical information","author":"Cao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109231_bib0008","series-title":"Sp","article-title":"Towards making systems forget with machine unlearning","author":"Cao","year":"2015"},{"key":"10.1016\/j.neunet.2026.109231_bib0009","series-title":"IJCAI","article-title":"Machine unlearning via null space calibration","author":"Chen","year":"2024"},{"key":"10.1016\/j.neunet.2026.109231_bib0010","series-title":"Aistats","article-title":"SIFU: Sequential informed federated unlearning for efficient and provable client unlearning in federated optimization","author":"Fraboni","year":"2024"},{"issue":"6","key":"10.1016\/j.neunet.2026.109231_bib0011","doi-asserted-by":"crossref","first-page":"5720","DOI":"10.1109\/TDSC.2024.3382321","article-title":"VeriFi: Towards verifiable federated unlearning","volume":"21","author":"Gao","year":"2024","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"10.1016\/j.neunet.2026.109231_bib0012","series-title":"AAAI","article-title":"Amnesiac machine learning","author":"Graves","year":"2021"},{"key":"10.1016\/j.neunet.2026.109231_bib0013","series-title":"IJCAI","article-title":"Unlearning during learning: An efficient federated machine unlearning method","author":"Gu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109231_bib0014","series-title":"CVPR","article-title":"Forgetting through transforming: Enabling federated unlearning via class-aware representation transformation","author":"Guo","year":"2025"},{"key":"10.1016\/j.neunet.2026.109231_bib0015","unstructured":"Halimi, A., Kadhe, S., Rawat, A., & Baracaldo, N. (2022). Federated unlearning: How to efficiently erase a client in fl?. arXiv preprint arXiv: 2207.05521."},{"key":"10.1016\/j.neunet.2026.109231_bib0016","series-title":"ICML","article-title":"Train faster, generalize better: Stability of stochastic gradient descent","author":"Hardt","year":"2016"},{"key":"10.1016\/j.neunet.2026.109231_bib0017","series-title":"ICML","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","author":"Karimireddy","year":"2020"},{"key":"10.1016\/j.neunet.2026.109231_bib0018","series-title":"NeurIPS","article-title":"Supervised contrastive learning","author":"Khosla","year":"2020"},{"key":"10.1016\/j.neunet.2026.109231_bib0019","series-title":"ICML","article-title":"Understanding black-box predictions via influence functions","author":"Koh","year":"2017"},{"key":"10.1016\/j.neunet.2026.109231_bib0020","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"11","key":"10.1016\/j.neunet.2026.109231_bib0021","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2026.109231_bib0022","unstructured":"Li, G., Shen, L., Sun, Y., Hu, Y., Hu, H., & Tao, D. (2023). Subspace based federated unlearning. arXiv preprint arXiv: 2302.12448."},{"key":"10.1016\/j.neunet.2026.109231_bib0023","series-title":"IWQOS","article-title":"Federaser: Enabling efficient client-level data removal from federated learning models","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109231_bib0024","series-title":"INFOCOM","article-title":"The right to be forgotten in federated learning: An efficient realization with rapid retraining","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109231_bib0025","series-title":"Federated learning: Privacy and incentive","article-title":"Threats to federated learning","author":"Lyu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109231_bib0026","series-title":"Aistats","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.neunet.2026.109231_bib0027","series-title":"ICAIIC","article-title":"Is client unlearning really necessary in federating learning?","author":"Mora","year":"2025"},{"key":"10.1016\/j.neunet.2026.109231_bib0028","series-title":"Introductory lectures on convex optimization: A basic course","volume":"vol. 87","author":"Nesterov","year":"2013"},{"key":"10.1016\/j.neunet.2026.109231_bib0029","series-title":"AAAI","article-title":"Federated unlearning with gradient descent and conflict mitigation","author":"Pan","year":"2025"},{"key":"10.1016\/j.neunet.2026.109231_bib0030","series-title":"NeurIPS","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"10.1016\/j.neunet.2026.109231_bib0031","series-title":"ICLR","article-title":"Label-agnostic forgetting: A supervision-free unlearning in deep models","author":"Shen","year":"2024"},{"key":"10.1016\/j.neunet.2026.109231_bib0032","series-title":"SP","article-title":"Membership inference attacks against machine learning models","author":"Shokri","year":"2017"},{"key":"10.1016\/j.neunet.2026.109231_bib0033","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"15164","article-title":"On the role of server momentum in federated learning","volume":"vol. 38","author":"Sun","year":"2024"},{"key":"10.1016\/j.neunet.2026.109231_bib0034","series-title":"AAAI","article-title":"FedProto: Federated prototype learning across heterogeneous clients","author":"Tan","year":"2022"},{"key":"10.1016\/j.neunet.2026.109231_bib0035","article-title":"FedPD: Defending federated prototype learning against backdoor attacks","volume":"184","author":"Tan","year":"2025","journal-title":"NN"},{"key":"10.1016\/j.neunet.2026.109231_bib0036","series-title":"NeurIPS","article-title":"Lipschitz regularity of deep neural networks: Analysis and efficient estimation","author":"Virmaux","year":"2018"},{"key":"10.1016\/j.neunet.2026.109231_bib0037","first-page":"10","article-title":"The EU general data protection regulation (GDPR)","volume":"10","author":"Voigt","year":"2017","journal-title":"A Practical Guide (1st Edition)"},{"key":"10.1016\/j.neunet.2026.109231_bib0038","series-title":"WWW","article-title":"Federated unlearning via class-discriminative pruning","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109231_bib0039","series-title":"ICML","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109231_bib0040","unstructured":"Wu, C., Zhu, S., & Mitra, P. (2022). Federated unlearning with knowledge distillation. arXiv preprint arXiv: 2201.09441."},{"key":"10.1016\/j.neunet.2026.109231_bib0041","series-title":"ICML","article-title":"DeltaGrad: Rapid retraining of machine learning models","author":"Wu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109231_bib0042","unstructured":"Xiao, H., Rasul, K., & Vollgraf, R. (2017). Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv: 1708.07747."},{"key":"10.1016\/j.neunet.2026.109231_bib0043","series-title":"ICDM","article-title":"Exact-fun: An exact and efficient federated unlearning approach","author":"Xiong","year":"2023"},{"key":"10.1016\/j.neunet.2026.109231_bib0044","series-title":"ICLR","article-title":"Personalized federated learning with feature alignment and classifier collaboration","author":"Xu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109231_bib0045","first-page":"4732","article-title":"Fedrecovery: Differentially private machine unlearning for federated learning frameworks","volume":"18","author":"Zhang","year":"2023","journal-title":"TIFS"},{"key":"10.1016\/j.neunet.2026.109231_bib0046","series-title":"ICLR","article-title":"Personalized federated learning with first order model optimization","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109231_bib0047","series-title":"CVPR","article-title":"Unlearning through knowledge overwriting: Reversible federated unlearning via selective sparse adapter","author":"Zhong","year":"2025"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026006921?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026006921?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:36:43Z","timestamp":1789083403000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026006921"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":47,"alternative-id":["S0893608026006921"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109231","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Margin-aware prototype learning for client withdrawal in federated unlearning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109231","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109231"}}