{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T18:01:22Z","timestamp":1773511282828,"version":"3.50.1"},"reference-count":71,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T00:00:00Z","timestamp":1714953600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFE0112600"],"award-info":[{"award-number":["2022YFE0112600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62293511 and 62394341"],"award-info":[{"award-number":["62293511 and 62394341"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Enflame Tech Co. Ltd"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Internet Technol."],"published-print":{"date-parts":[[2024,5,31]]},"abstract":"<jats:p>Vertical federated learning (VFL) revolutionizes privacy-preserved collaboration for small businesses that have distinct but complementary feature sets. However, as the scope of VFL expands, the constant entering and leaving of participants and the subsequent exercise of the \u201cright to be forgotten\u201d pose a great challenge in practice. The question of how to efficiently erase one\u2019s contribution from the shared model remains largely unexplored in the context of VFL. In this article, we introduce a vertical federated unlearning framework, which integrates model checkpointing techniques with a hybrid, first-order optimization technique. The core concept is to reduce backpropagation time and improve convergence\/generalization by combining the advantages of the existing optimizers. We provide in-depth theoretical analysis and time complexity to illustrate the effectiveness of the proposed design. We conduct extensive experiments on six public datasets and demonstrate that our method could achieve up to 6.3\u00d7 speedup compared to the baseline, with negligible influence on the original learning task.<\/jats:p>","DOI":"10.1145\/3657290","type":"journal-article","created":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T12:26:10Z","timestamp":1712751970000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Efficient Vertical Federated Unlearning via Fast Retraining"],"prefix":"10.1145","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8999-6358","authenticated-orcid":false,"given":"Zichen","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8335-2746","authenticated-orcid":false,"given":"Xiangshan","family":"Gao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4818-3797","authenticated-orcid":false,"given":"Cong","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4221-2162","authenticated-orcid":false,"given":"Peng","family":"Cheng","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3155-3145","authenticated-orcid":false,"given":"Jiming","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2024,5,6]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"A. Krizhevsky and G. Hinton. 2009. Learning multiple layers of features from tiny images. Handbook of Systemic Autoimmune Diseases 1 4 (2009)."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717761"},{"key":"e_1_3_2_4_2","first-page":"3513","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019 (NeurIPS\u201919)","author":"Antonio Ginart","year":"2019","unstructured":"Ginart Antonio, Y. Guan Melody, Valiant Gregory, and Zou James. 2019. Making AI forget you: Data deletion in machine learning. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019 (NeurIPS\u201919). 3513\u20133526."},{"key":"e_1_3_2_5_2","first-page":"4148","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Ashia C. Wilson","year":"2017","unstructured":"C. Wilson Ashia, Roelofs Rebecca, Stern Mitchell, Srebro Nati, and Recht Benjamin. 2017. The marginal value of adaptive gradient methods in machine learning. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017. 4148\u20134158."},{"key":"e_1_3_2_6_2","volume-title":"5th International Conference on Learning Representations (ICLR\u201917), Conference Track Proceedings","author":"Chiyuan Zhang","year":"2017","unstructured":"Zhang Chiyuan, Bengio Samy, Hardt Moritz, Recht Benjamin, and Vinyals Oriol. 2017. Understanding deep learning requires rethinking generalization. In 5th International Conference on Learning Representations (ICLR\u201917), Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_7_2","series-title":"Proceedings of Machine Learning Research","first-page":"3832","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML\u201920)","volume":"119","author":"Chuan Guo","year":"2020","unstructured":"Guo Chuan, Goldstein Tom, Y. Hannun Awni, and van der Maaten Laurens. 2020. Certified data removal from machine learning models. In Proceedings of the 37th International Conference on Machine Learning (ICML\u201920)(Proceedings of Machine Learning Research, Vol. 119). PMLR, 3832\u20133842."},{"key":"e_1_3_2_8_2","volume-title":"3rd International Conference on Learning Representations (ICLR\u201915), Conference Track Proceedings","author":"Diederik P. Kingma","year":"2015","unstructured":"P. Kingma Diederik and Ba Jimmy. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations (ICLR\u201915), Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.3390\/a15040104"},{"key":"e_1_3_2_10_2","volume-title":"International Conference on Learning Representations","author":"Foret Pierre","unstructured":"Pierre Foret, Ariel Kleiner, Hossein Mobahi, and Behnam Neyshabur. [n. d.]. Sharpness-aware minimization for efficiently improving generalization. In International Conference on Learning Representations."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3382321"},{"key":"e_1_3_2_12_2","unstructured":"Badih Ghazi Noah Golowich Ravi Kumar Pasin Manurangsi and Chiyuan Zhang. 2021. Deep Learning with Label Differential Privacy. arxiv:2102.06062 [cs.LG]"},{"key":"e_1_3_2_13_2","unstructured":"Hanlin Gu Jiahuan Luo Yan Kang Lixin Fan and Qiang Yang. 2023. FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscation. arxiv:2301.12623 [cs.DC]"},{"key":"e_1_3_2_14_2","article-title":"Federated learning of deep networks using model averaging","volume":"1602","author":"Brendan McMahan H.","year":"2016","unstructured":"McMahan H. Brendan, Moore Eider, Ramage Daniel, and Ag\u00fcera y Arcas Blaise. 2016. Federated learning of deep networks using model averaging. CoRR abs\/1602.05629 (2016). arXiv:1602.05629http:\/\/arxiv.org\/abs\/1602.05629","journal-title":"CoRR"},{"key":"e_1_3_2_15_2","article-title":"A federated learning framework for smart grids: Securing power traces in collaborative learning","volume":"2103","author":"Haizhou Liu","year":"2021","unstructured":"Liu Haizhou, Zhang Xuan, Shen Xinwei, and Sun Hongbin. 2021. A federated learning framework for smart grids: Securing power traces in collaborative learning. CoRR abs\/2103.11870 (2021). arXiv:2103.11870https:\/\/arxiv.org\/abs\/2103.11870","journal-title":"CoRR"},{"key":"e_1_3_2_16_2","unstructured":"Anisa Halimi Swanand Kadhe Ambrish Rawat and Nathalie Baracaldo. 2022. Federated unlearning: How to efficiently erase a client in FL? arXiv:2207.05521 [cs.LG]."},{"issue":"3","key":"e_1_3_2_17_2","doi-asserted-by":"crossref","first-page":"234","DOI":"10.69554\/TCFN5165","article-title":"Understanding the scope and impact of the California Consumer Privacy Act of 2018","volume":"2","author":"Harding Elizabeth (Liz)","year":"2019","unstructured":"Elizabeth (Liz) Harding, Jarno J. Vanto, Reece Clark, L. Hannah Ji, and Sara C. Ainsworth. 2019. Understanding the scope and impact of the California Consumer Privacy Act of 2018. Journal of Data Protection & Privacy 2, 3 (March2019), 234\u2013253.","journal-title":"Journal of Data Protection & Privacy"},{"key":"e_1_3_2_18_2","series-title":"JMLR Workshop and Conference Proceedings","first-page":"1139","volume-title":"Proceedings of the 30th International Conference on Machine Learning (ICML\u201913)","volume":"28","author":"Ilya Sutskever","year":"2013","unstructured":"Sutskever Ilya, Martens James, E. Dahl George, and E. Hinton Geoffrey. 2013. On the importance of initialization and momentum in deep learning. In Proceedings of the 30th International Conference on Machine Learning (ICML\u201913)(JMLR Workshop and Conference Proceedings, Vol. 28). JMLR.org, 1139\u20131147."},{"key":"e_1_3_2_19_2","series-title":"Proceedings of Machine Learning Research","first-page":"2008","volume-title":"Proceedings of the 24th International Conference on Artificial Intelligence and Statistics","volume":"130","author":"Izzo Zachary","year":"2021","unstructured":"Zachary Izzo, Mary Anne Smart, Kamalika Chaudhuri, and James Zou. 2021. Approximate data deletion from machine learning models. In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics(Proceedings of Machine Learning Research, Vol. 130). PMLR, 2008\u20132016."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2021068"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512222"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00482"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_25_2","article-title":"Vertical federated learning: Challenges, methodologies and experiments","volume":"2202","author":"Kang Wei","year":"2022","unstructured":"Wei Kang, Li Jun, Ma Chuan, Ding Ming, Wei Sha, Wu Fan, Chen Guihai, and Ranbaduge Thilina. 2022. Vertical federated learning: Challenges, methodologies and experiments. CoRR abs\/2202.04309 (2022). arXiv:2202.04309https:\/\/arxiv.org\/abs\/2202.04309","journal-title":"CoRR"},{"key":"e_1_3_2_26_2","volume-title":"The Right to Be Forgotten: A Comparative Study of the Emergent Right\u2019s Evolution and Application in Europe, the Americas, and Asia","author":"Kornbeck Dr. Jacob","year":"2021","unstructured":"Dr. Jacob Kornbeck. 2021. The Right to Be Forgotten: A Comparative Study of the Emergent Right\u2019s Evolution and Application in Europe, the Americas, and Asia. Vol. 4. 436\u2013438."},{"key":"e_1_3_2_27_2","unstructured":"Frederik Kunstner Philipp Hennig and Lukas Balles. 2019. Limitations of the empirical Fisher approximation for natural gradient descent. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems (NeurIPS\u201919) Vancouver BC Canada. 4158\u20134169."},{"key":"e_1_3_2_28_2","unstructured":"Tian Li Anit Kumar Sahu Manzil Zaheer Maziar Sanjabi Ameet Talwalkar and Virginia Smith. 2020. Federated Optimization in Heterogeneous Networks. In Proceedings of Machine Learning and Systems I. Dhillon D. Papailiopoulos and V. Sze (Eds.). 2 (2020) 429\u2013450. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2020\/file\/1f5fe83998a09396ebe6477d9475ba0c-Paper.pdf"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom50675.2020.00098"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521274"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796721"},{"key":"e_1_3_2_32_2","volume-title":"8th International Conference on Learning Representations (ICLR\u201920)","author":"Liyuan Liu","year":"2020","unstructured":"Liu Liyuan, Jiang Haoming, He Pengcheng, Chen Weizhu, Liu Xiaodong, Gao Jianfeng, and Han Jiawei. 2020. On the variance of the adaptive learning rate and beyond. In 8th International Conference on Learning Representations (ICLR\u201920)."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00019"},{"key":"e_1_3_2_34_2","article-title":"ADADELTA: An adaptive learning rate method","volume":"1212","author":"Matthew D. Zeiler","year":"2012","unstructured":"D. Zeiler Matthew. 2012. ADADELTA: An adaptive learning rate method. CoRR abs\/1212.5701 (2012). arXiv:1212.5701http:\/\/arxiv.org\/abs\/1212.5701","journal-title":"CoRR"},{"key":"e_1_3_2_35_2","series-title":"Proceedings of Machine Learning Research","first-page":"1273","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","volume":"54","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(Proceedings of Machine Learning Research, Vol. 54). PMLR, 1273\u20131282."},{"key":"e_1_3_2_36_2","series-title":"JMLR Workshop and Conference Proceedings","first-page":"1225","volume-title":"Proceedings of the 33nd International Conference on Machine Learning (ICML\u201916)","volume":"48","author":"Moritz Hardt","year":"2016","unstructured":"Hardt Moritz, Recht Ben, and Singer Yoram. 2016. Train faster, generalize better: Stability of stochastic gradient descent. In Proceedings of the 33nd International Conference on Machine Learning (ICML\u201916)(JMLR Workshop and Conference Proceedings, Vol. 48). JMLR.org, 1225\u20131234. http:\/\/proceedings.mlr.press\/v48\/hardt16.html"},{"key":"e_1_3_2_37_2","unstructured":"Masoud Nickparvar. 2021. Brain Tumor MRI Dataset. https:\/\/www.kaggle.com\/datasets\/masoudnickparvar\/brain-tumor-mri-dataset"},{"key":"e_1_3_2_38_2","article-title":"Improving generalization performance by switching from Adam to SGD","volume":"1712","author":"Nitish Shirish Keskar","year":"2017","unstructured":"Shirish Keskar Nitish and Socher Richard. 2017. Improving generalization performance by switching from Adam to SGD. CoRR abs\/1712.07628 (2017). arXiv:1712.07628http:\/\/arxiv.org\/abs\/1712.07628","journal-title":"CoRR"},{"key":"e_1_3_2_39_2","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","volume":"1804","author":"Pete Warden","year":"2018","unstructured":"Warden Pete. 2018. Speech commands: A dataset for limited-vocabulary speech recognition. CoRR abs\/1804.03209 (2018). arXiv:1804.03209http:\/\/arxiv.org\/abs\/1804.03209","journal-title":"CoRR"},{"key":"e_1_3_2_40_2","article-title":"Split learning for health: Distributed deep learning without sharing raw patient data","volume":"1812","author":"Praneeth Vepakomma","year":"2018","unstructured":"Vepakomma Praneeth, Gupta Otkrist, Swedish Tristan, and Raskar Ramesh. 2018. Split learning for health: Distributed deep learning without sharing raw patient data. CoRR abs\/1812.00564 (2018). arXiv:1812.00564http:\/\/arxiv.org\/abs\/1812.00564","journal-title":"CoRR"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Pengyu Qiu Xuhong Zhang Shouling Ji Tianyu Du Yuwen Pu Jun Zhou and Ting Wang. 2023. Your labels are selling you out: Relation leaks in vertical federated learning. IEEE Trans. Dependable Secur. Comput. 20 5 (2023) 3653\u20133668. 10.1109\/TDSC.2022.3208630","DOI":"10.1109\/TDSC.2022.3208630"},{"key":"e_1_3_2_42_2","article-title":"PyVertical: A vertical federated learning framework for multi-headed SplitNN","volume":"2104","author":"Romanini Daniele","year":"2021","unstructured":"Daniele Romanini, James Hall Adam, Papadopoulos Pavlos, Titcombe Tom, Ismail Abbas, Cebere Tudor, Sandmann Robert, Roehm Robin, and A. Hoeh Michael. 2021. PyVertical: A vertical federated learning framework for multi-headed SplitNN. CoRR abs\/2104.00489 (2021). arXiv:2104.00489https:\/\/arxiv.org\/abs\/2104.00489","journal-title":"CoRR"},{"key":"e_1_3_2_43_2","article-title":"An overview of gradient descent optimization algorithms","volume":"1609","author":"Sebastian Ruder","year":"2016","unstructured":"Ruder Sebastian. 2016. An overview of gradient descent optimization algorithms. CoRR abs\/1609.04747 (2016). arXiv:1609.04747http:\/\/arxiv.org\/abs\/1609.04747","journal-title":"CoRR"},{"key":"e_1_3_2_44_2","unstructured":"SSNL and Apaszke. 2018. A Case of Traffic Violations Insurance-using Federated Learning. https:\/\/github.com\/pytorch\/pytorch\/issues\/7343"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57959-7"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3023905"},{"key":"e_1_3_2_48_2","unstructured":"Jianyu Wang Qinghua Liu Hao Liang Gauri Joshi and H. Vincent Poor. 2020. Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization. arxiv:2007.07481 [cs.LG]"},{"key":"e_1_3_2_49_2","unstructured":"WeBank. 2019. A Case of Traffic Violations Insurance-using Federated Learning. https:\/\/www.fedai.org\/cases\/"},{"key":"e_1_3_2_50_2","unstructured":"WeBank. 2019. Utilization of FATE in Risk Management of Credit in Small and Micro Enterprises. https:\/\/www.fedai.org\/cases\/"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295170"},{"key":"e_1_3_2_53_2","article-title":"Federated unlearning with knowledge distillation","volume":"2201","author":"Wu Chen","year":"2022","unstructured":"Chen Wu, Sencun Zhu, and Prasenjit Mitra. 2022. Federated unlearning with knowledge distillation. CoRR abs\/2201.09441 (2022). arXiv:2201.09441https:\/\/arxiv.org\/abs\/2201.09441","journal-title":"CoRR"},{"key":"e_1_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Wenxuan Wu Zhongang Qi and Fuxin Li. 2019. PointConv: Deep convolutional networks on 3D point clouds. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201919) 9613\u20139622.","DOI":"10.1109\/CVPR.2019.00985"},{"key":"e_1_3_2_55_2","first-page":"10355","volume-title":"International Conference on Machine Learning","author":"Wu Yinjun","year":"2020","unstructured":"Yinjun Wu, Edgar Dobriban, and Susan Davidson. 2020. Deltagrad: Rapid retraining of machine learning models. In International Conference on Machine Learning. PMLR, 10355\u201310366."},{"key":"e_1_3_2_56_2","doi-asserted-by":"crossref","first-page":"1912","DOI":"10.1109\/CVPR.2015.7298801","article-title":"3D ShapeNets: A deep representation for volumetric shapes","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3D ShapeNets: A deep representation for volumetric shapes. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915), 1912\u20131920.","journal-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915)"},{"key":"e_1_3_2_57_2","article-title":"CAFE: Catastrophic data leakage in vertical federated learning","volume":"2110","author":"Xiao Jin","year":"2021","unstructured":"Jin Xiao, Chen Pin-Yu, Hsu Chia-Yi, Yu Chia-Mu, and Chen Tianyi. 2021. CAFE: Catastrophic data leakage in vertical federated learning. CoRR abs\/2110.15122 (2021). arXiv:2110.15122https:\/\/arxiv.org\/abs\/2110.15122","journal-title":"CoRR"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","unstructured":"Haonan Yan Xiaoguang Li Ziyao Guo Hui Li Fenghua Li and Xiaodong Lin. 2022. ARCANE: An efficient architecture for exact machine unlearning. 3981\u20133988. DOI:10.24963\/ijcai.2022\/553","DOI":"10.24963\/ijcai.2022\/553"},{"key":"e_1_3_2_59_2","article-title":"FedMVT: Semi-supervised vertical federated learning with MultiView training","volume":"2008","author":"Yan Kang","year":"2020","unstructured":"Kang Yan, Liu Yang, and Chen Tianjian. 2020. FedMVT: Semi-supervised vertical federated learning with MultiView training. CoRR abs\/2008.10838 (2020). arXiv:2008.10838https:\/\/arxiv.org\/abs\/2008.10838","journal-title":"CoRR"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3198176"},{"key":"e_1_3_2_61_2","article-title":"Asymmetrical vertical federated learning","volume":"2004","author":"Yang Liu","year":"2020","unstructured":"Liu Yang, Zhang Xiong, and Wang Libin. 2020. Asymmetrical vertical federated learning. CoRR abs\/2004.07427 (2020). arXiv:2004.07427https:\/\/arxiv.org\/abs\/2004.07427","journal-title":"CoRR"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.12814"},{"key":"e_1_3_2_63_2","article-title":"Learn to forget: User-level memorization elimination in federated learning","volume":"2003","author":"Yang Liu","year":"2020","unstructured":"Liu Yang, Ma Zhuo, Liu Ximeng, and Ma Jianfeng. 2020. Learn to forget: User-level memorization elimination in federated learning. CoRR abs\/2003.10933 (2020). arXiv:2003.10933https:\/\/arxiv.org\/abs\/2003.10933","journal-title":"CoRR"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_65_2","article-title":"RMSProp and equilibrated adaptive learning rates for non-convex optimization","volume":"1502","author":"Yann N. Dauphin","year":"2015","unstructured":"N. Dauphin Yann, de Vries Harm, Chung Junyoung, and Bengio Yoshua. 2015. RMSProp and equilibrated adaptive learning rates for non-convex optimization. CoRR abs\/1502.04390 (2015). arXiv:1502.04390http:\/\/arxiv.org\/abs\/1502.04390","journal-title":"CoRR"},{"key":"e_1_3_2_66_2","volume-title":"8th International Conference on Learning Representations (ICLR\u201920)","author":"Yiding Jiang","year":"2020","unstructured":"Jiang Yiding, Neyshabur Behnam, Mobahi Hossein, Krishnan Dilip, and Bengio Samy. 2020. Fantastic generalization measures and where to find them. In 8th International Conference on Learning Representations (ICLR\u201920). OpenReview.net."},{"key":"e_1_3_2_67_2","series-title":"Proceedings of Machine Learning Research","first-page":"10355","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML\u201920)","volume":"119","author":"Yinjun Wu","year":"2020","unstructured":"Wu Yinjun, Dobriban Edgar, and B. Davidson Susan. 2020. DeltaGrad: Rapid retraining of machine learning models. In Proceedings of the 37th International Conference on Machine Learning (ICML\u201920)(Proceedings of Machine Learning Research, Vol. 119). PMLR, 10355\u201310366."},{"key":"e_1_3_2_68_2","volume-title":"9th International Conference on Learning Representations (ICLR\u201921)","author":"Zeke Xie","year":"2021","unstructured":"Xie Zeke, Sato Issei, and Sugiyama Masashi. 2021. A diffusion theory for deep learning dynamics: Stochastic gradient descent exponentially favors flat minima. In 9th International Conference on Learning Representations (ICLR\u201921). OpenReview.net."},{"key":"e_1_3_2_69_2","article-title":"On the power-law spectrum in deep learning: A bridge to protein science","volume":"2201","author":"Zeke Xie","year":"2022","unstructured":"Xie Zeke, Tang Qian-Yuan, Cai Yunfeng, Sun Mingming, and Li Ping. 2022. On the power-law spectrum in deep learning: A bridge to protein science. CoRR abs\/2201.13011 (2022). https:\/\/arxiv.org\/abs\/2201.13011","journal-title":"CoRR"},{"key":"e_1_3_2_70_2","series-title":"Proceedings of Machine Learning Research","first-page":"24430","volume-title":"International Conference on Machine Learning (ICML\u201922)","volume":"162","author":"Zeke Xie","year":"2022","unstructured":"Xie Zeke, Wang Xinrui, Zhang Huishuai, Sato Issei, and Sugiyama Masashi. 2022. Adaptive inertia: Disentangling the effects of adaptive learning rate and momentum. In International Conference on Machine Learning (ICML\u201922)(Proceedings of Machine Learning Research, Vol. 162). PMLR, 24430\u201324459."},{"key":"e_1_3_2_71_2","first-page":"10665","volume-title":"35th AAAI Conference on Artificial Intelligence (AAAI\u201921)","author":"Zhewei Yao","year":"2021","unstructured":"Yao Zhewei, Gholami Amir, Shen Sheng, Mustafa Mustafa, Keutzer Kurt, and W. Mahoney Michael. 2021. ADAHESSIAN: An adaptive second order optimizer for machine learning. In 35th AAAI Conference on Artificial Intelligence (AAAI\u201921). AAAI Press, 10665\u201310673."},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3192121"}],"container-title":["ACM Transactions on Internet Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3657290","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3657290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:39Z","timestamp":1750295859000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3657290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,6]]},"references-count":71,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,5,31]]}},"alternative-id":["10.1145\/3657290"],"URL":"https:\/\/doi.org\/10.1145\/3657290","relation":{},"ISSN":["1533-5399","1557-6051"],"issn-type":[{"value":"1533-5399","type":"print"},{"value":"1557-6051","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,6]]},"assertion":[{"value":"2023-06-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-05","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}