{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:49:52Z","timestamp":1776181792682,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021YFB2401300"],"award-info":[{"award-number":["2021YFB2401300"]}]},{"name":"National Key Research and Development Program of China","award":["2020YFA0713900"],"award-info":[{"award-number":["2020YFA0713900"]}]},{"name":"National Key Research and Development Program of China","award":["2022YFA1004100"],"award-info":[{"award-number":["2022YFA1004100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772410"],"award-info":[{"award-number":["61772410"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802298"],"award-info":[{"award-number":["61802298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62166031"],"award-info":[{"award-number":["62166031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172329"],"award-info":[{"award-number":["62172329"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811461"],"award-info":[{"award-number":["U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A6005"],"award-info":[{"award-number":["U21A6005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11690011"],"award-info":[{"award-number":["11690011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Plan Project of Henan province","award":["232102211007"],"award-info":[{"award-number":["232102211007"]}]},{"name":"Scientific Studies of Higher Education Institution of Henan province","award":["23B520006"],"award-info":[{"award-number":["23B520006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tpami.2023.3332428","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:17:21Z","timestamp":1699903041000},"page":"1243-1256","source":"Crossref","is-referenced-by-count":27,"title":["Multi-Stage Asynchronous Federated Learning With Adaptive Differential Privacy"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6321-2567","authenticated-orcid":false,"given":"Yanan","family":"Li","sequence":"first","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics (NEL-BDA), Xi’an Jiaotong University, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4495-6237","authenticated-orcid":false,"given":"Shusen","family":"Yang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics (NEL-BDA), Xi’an Jiaotong University, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6498-0250","authenticated-orcid":false,"given":"Xuebin","family":"Ren","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics (NEL-BDA), Xi’an Jiaotong University, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5660-1655","authenticated-orcid":false,"given":"Liang","family":"Shi","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics (NEL-BDA), Xi’an Jiaotong University, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9002-4350","authenticated-orcid":false,"given":"Cong","family":"Zhao","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics (NEL-BDA), Xi’an Jiaotong University, Shaanxi, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-93030-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00364-5"},{"key":"ref3","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3137364"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006179"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-23551-2_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref8","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Recht"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/140961134"},{"key":"ref10","first-page":"6182","article-title":"Asynchronous coordinate descent under more realistic assumptions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref11","first-page":"1701","article-title":"Asynchronous distributed admm for consensus optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref12","article-title":"More iterations per second, same quality\u2013why asynchronous algorithms may drastically outperform traditional ones","author":"Hannah","year":"2017"},{"key":"ref13","article-title":"Asynchronous federated optimization","author":"Xie","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2942179"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2022.23054"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2594132"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"ref20","article-title":"Differentially private federated learning: A client level perspective","author":"Geyer"},{"key":"ref21","first-page":"7564","article-title":"cpSGD: Communication-efficient and differentially-private distributed SGD","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Agarwal"},{"key":"ref22","first-page":"1","article-title":"Learning differentially private recurrent language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"McMahan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"key":"ref24","article-title":"AdaClip: Adaptive clipping for private SGD","author":"Pichapati","year":"2019"},{"key":"ref25","first-page":"17455","article-title":"Differentially private learning with adaptive clipping","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Andrew"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107796"},{"key":"ref27","article-title":"Leaf: A benchmark for federated settings","author":"Caldas","year":"2018"},{"key":"ref28","first-page":"3581","article-title":"Federated learning with buffered asynchronous aggregation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Nguyen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton49937.2022.9929409"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2787987"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3089713"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00029"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737416"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3056991"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"ref38","article-title":"A general approach to adding differential privacy to iterative training procedures","author":"McMahan","year":"2018"},{"key":"ref39","article-title":"Asynchronous federated learning with reduced number of rounds and with differential privacy from less aggregated Gaussian noise","author":"van Dijk","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3101991"},{"key":"ref41","first-page":"1","article-title":"Understanding gradient clipping in private SGD: A geometric perspective","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2942179"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1561\/2200000050"},{"key":"ref44","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dean"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3103770"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118435"},{"issue":"1","key":"ref48","first-page":"9613","article-title":"The error-feedback framework: Better rates for SGD with delayed gradients and compressed updates","volume":"21","author":"Stich","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","first-page":"957","article-title":"AdaDelay: Delay adaptive distributed stochastic optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Sra"},{"key":"ref50","first-page":"24093","article-title":"Delay-adaptive step-sizes for asynchronous learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref51","first-page":"4120","article-title":"Asynchronous stochastic gradient descent with delay compensation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9411917"},{"key":"ref53","first-page":"9024","article-title":"Asynchronous stochastic optimization robust to arbitrary delays","volume":"34","author":"Cohen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref54","first-page":"420","article-title":"Asynchronous SGD beats minibatch sgd under arbitrary delays","volume":"35","author":"Mishchenko","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref55","first-page":"17202","article-title":"Sharper convergence guarantees for asynchronous SGD for distributed and federated learning","volume":"35","author":"Koloskova","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref56","article-title":"Differentially private learning with adaptive clipping","author":"Thakkar","year":"2019"},{"key":"ref57","first-page":"6280","article-title":"Privacy amplification by subsampling: Tight analyses via couplings and divergences","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Balle"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.14778\/3579075.3579081"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s00287-019-01205-x"},{"key":"ref60","first-page":"16070","article-title":"Attack of the tails: Yes, you really can backdoor federated learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref61","article-title":"Can you really backdoor federated learning?","author":"Sun","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671910"},{"key":"ref63","first-page":"11372","article-title":"CRFL: Certifiably robust federated learning against backdoor attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref64","first-page":"1","article-title":"Flame: Taming backdoors in federated learning","volume-title":"Proc. USENIX Secur.","author":"Thien Duc"},{"key":"ref65","first-page":"7587","article-title":"SparseFed: Mitigating model poisoning attacks in federated learning with sparsification","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Panda"},{"key":"ref66","first-page":"7948","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Banner"},{"key":"ref67","first-page":"493","article-title":"Batchcrypt: Efficient homomorphic encryption for cross-silo federated learning","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Zhang"},{"key":"ref68","article-title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","author":"Zhang","year":"2019"},{"key":"ref69","article-title":"Three tools for practical differential privacy","author":"van der Veen","year":"2018"},{"key":"ref70","first-page":"20461","article-title":"On large-cohort training for federated learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Charles"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467268"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3150579"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1137\/16M1057000"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10384454\/10316599.pdf?arnumber=10316599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:49:36Z","timestamp":1705024176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10316599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":73,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3332428","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}