{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:12:12Z","timestamp":1753884732355,"version":"3.41.2"},"reference-count":32,"publisher":"World Scientific Pub Co Pte Ltd","issue":"06","funder":[{"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"}]},{"name":"Major Project of the University","award":["ZK16118"],"award-info":[{"award-number":["ZK16118"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Wavelets Multiresolut Inf. Process."],"published-print":{"date-parts":[[2023,11]]},"abstract":"<jats:p> Federated learning (FL) is an important approach to cooperate with multiple devices for learning without exchanging data between devices and central server. However, due to bandwidth and other reasons, the communication efficiency should be considered when the volume of information transmitted is limited. In this paper, we utilize the tool of lattice quantization form quantization theory and the variable intercommunication interval to improve communication efficiency. Meanwhile, to make strong privacy guarantee, we incorporate the notion of differential privacy (DP) to the FL framework with local SGD algorithm. By adding calibrated noises, we propose a universal lattice quantization for differentially private federated averaging algorithm (ULQ-DP-FedAvg). We provide tight privacy bound by using some privacy techniques. We also analyze the convergence bound of ULQ-DP-FedAvg based on bits rate constraints and the growing inter-communication interval as well as the data are non-independent identically distribution (Non-IID). It turns out that the algorithm converges and preserves that the privacy has scarcely influenced on the convergence rate. The effectiveness of our algorithm is demonstrated by synthetic and real datasets. <\/jats:p>","DOI":"10.1142\/s0219691323500200","type":"journal-article","created":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T08:52:13Z","timestamp":1680252733000},"source":"Crossref","is-referenced-by-count":4,"title":["Privacy-preserving federated learning on lattice quantization"],"prefix":"10.1142","volume":"21","author":[{"given":"Lingjie","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Mathematics, Northwest University, Xi\u2019an, 710127, P. R. China"},{"name":"School of Mathematics and Information Science, Baoji University of Arts and Sciences, Baoji, 721000, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1437-1729","authenticated-orcid":false,"given":"Hai","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mathematics, Northwest University, Xi\u2019an, 710127, P. R. China"}]}],"member":"219","published-online":{"date-parts":[[2023,5,15]]},"reference":[{"key":"S0219691323500200BIB002","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1109\/ISIT44484.2020.9174133","volume-title":"2020 IEEE Int. Symp. Information Theory (ISIT)","author":"Asoodeh S.","year":"2020"},{"key":"S0219691323500200BIB003","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Balle B.","year":"2018"},{"issue":"1","key":"S0219691323500200BIB004","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1109\/JSAIT.2020.2985917","volume":"1","author":"Basu D.","year":"2020","journal-title":"IEEE J. Sel. Areas Inf. Theory"},{"key":"S0219691323500200BIB006","first-page":"177","volume-title":"Proc. COMPSTAT\u20192010","author":"Bottou L.","year":"2010"},{"key":"S0219691323500200BIB007","first-page":"27:1","volume":"2","author":"Chang C.-C.","year":"2011","journal-title":"ACM Trans. Intell. Sys. Technol."},{"issue":"1","key":"S0219691323500200BIB008","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1109\/TWC.2020.3024629","volume":"20","author":"Chen M.","year":"2020","journal-title":"IEEE Trans. Wirel. Commun."},{"issue":"17","key":"S0219691323500200BIB009","doi-asserted-by":"crossref","first-page":"e2024789118","DOI":"10.1073\/pnas.2024789118","volume":"118","author":"Chen M.","year":"2021","journal-title":"Proc. Natl. Acad. Sci."},{"key":"S0219691323500200BIB010","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/11681878_14","volume-title":"Theory of cryptography Conf.","author":"Dwork C.","year":"2006"},{"issue":"3","key":"S0219691323500200BIB011","first-page":"211","volume":"9","author":"Dwork C.","year":"2014","journal-title":"Found. Trends Theor. Comput. Sci."},{"key":"S0219691323500200BIB012","doi-asserted-by":"crossref","first-page":"2468","DOI":"10.1137\/1.9781611975482.151","volume-title":"Proc. Thirtieth Annual ACM-SIAM Symp. Discrete Algorithms","author":"Erlingsson \u00da.","year":"2019"},{"key":"S0219691323500200BIB013","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1109\/FOCS.2018.00056","volume-title":"2018 IEEE 59th Annual Symp. Foundations of Computer Science (FOCS)","author":"Feldman V.","year":"2018"},{"issue":"1","key":"S0219691323500200BIB014","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1109\/JSAIT.2021.3056102","volume":"2","author":"Girgis A. M","year":"2021","journal-title":"IEEE J. Sel. Areas Inf. Theory"},{"key":"S0219691323500200BIB015","first-page":"1049","volume":"32","author":"Haddadpour F.","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0219691323500200BIB017","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1007\/978-3-319-46128-1_50","volume-title":"Joint European Conf. Machine Learning and Knowledge Discovery in Databases","author":"Karimi H.","year":"2016"},{"key":"S0219691323500200BIB018","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1109\/82.553397","volume":"43","author":"Kirac A.","year":"1996","journal-title":"IEEE Trans. Circuits Syst. II, Analog Digital Signal Process."},{"key":"S0219691323500200BIB022","first-page":"429","volume":"2","author":"Li T.","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"S0219691323500200BIB026","first-page":"1273","volume-title":"Artificial intelligence and Statistics","author":"McMahan B.","year":"2017"},{"key":"S0219691323500200BIB027","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/CSF.2017.11","volume-title":"2017 IEEE 30th Computer Security Foundations Symp. (CSF)","author":"Mironov I.","year":"2017"},{"issue":"4","key":"S0219691323500200BIB028","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1137\/070704277","volume":"19","author":"Nemirovski A.","year":"2009","journal-title":"SIAM J.Optim."},{"key":"S0219691323500200BIB030","first-page":"2021","volume-title":"Int. Conf. Artificial Intelligence and Statistics","author":"Reisizadeh A.","year":"2020"},{"key":"S0219691323500200BIB031","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1007\/s00245-019-09617-7","volume":"82","author":"Rosasco L.","year":"2020","journal-title":"Appl. Math. Optim."},{"key":"S0219691323500200BIB032","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TSP.2020.3046971","volume":"69","author":"Shlezinger N.","year":"2020","journal-title":"IEEE Trans. Signal Process."},{"key":"S0219691323500200BIB033","first-page":"4427","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems NIPS\u201917","author":"Smith V.","year":"2017"},{"key":"S0219691323500200BIB034","first-page":"796","volume-title":"2020 IEEE Int. Symp. Information Theory (ISIT)","author":"Sordello M.","year":"2021"},{"key":"S0219691323500200BIB035","first-page":"24313","volume":"34","author":"Spiridonoff A.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0219691323500200BIB037","first-page":"1","volume":"22","author":"Wang J.","year":"213","journal-title":"J. Mach. Learn. Res."},{"key":"S0219691323500200BIB038","first-page":"1226","volume-title":"The 22nd Int. Conf. Artificial Intelligence and Statistics","author":"Wang Y.-X.","year":"2019"},{"issue":"489","key":"S0219691323500200BIB039","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1198\/jasa.2009.tm08651","volume":"105","author":"Wasserman L.","year":"2010","journal-title":"J. Amer. Stat. Assoc."},{"issue":"2","key":"S0219691323500200BIB040","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1109\/18.119699","volume":"38","author":"Zamir R.","year":"1992","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"4","key":"S0219691323500200BIB041","doi-asserted-by":"crossref","first-page":"1152","DOI":"10.1109\/18.508838","volume":"42","author":"Zamir R.","year":"1996","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"1","key":"S0219691323500200BIB042","first-page":"3321","volume":"14","author":"Zhang Y.","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"S0219691323500200BIB043","first-page":"7634","volume-title":"Int. Conf. Machine Learning","author":"Zhu Y.","year":"2019"}],"container-title":["International Journal of Wavelets, Multiresolution and Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0219691323500200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T04:34:39Z","timestamp":1693974879000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0219691323500200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,15]]},"references-count":32,"journal-issue":{"issue":"06","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["10.1142\/S0219691323500200"],"URL":"https:\/\/doi.org\/10.1142\/s0219691323500200","relation":{},"ISSN":["0219-6913","1793-690X"],"issn-type":[{"type":"print","value":"0219-6913"},{"type":"electronic","value":"1793-690X"}],"subject":[],"published":{"date-parts":[[2023,5,15]]},"article-number":"2350020"}}