{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:54:31Z","timestamp":1764960871273,"version":"3.46.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306198"],"award-info":[{"award-number":["62306198"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2024NSFSC1468"],"award-info":[{"award-number":["2024NSFSC1468"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tnnls.2025.3539869","type":"journal-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T13:58:19Z","timestamp":1740578299000},"page":"14922-14936","source":"Crossref","is-referenced-by-count":1,"title":["E-3SFC: Communication-Efficient Federated Learning With Double-Way Features Synthesizing"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8074-6416","authenticated-orcid":false,"given":"Yuhao","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Computer Science and the Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3706-3462","authenticated-orcid":false,"given":"Yuxin","family":"Tian","sequence":"additional","affiliation":[{"name":"College of Computer Science and the Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9988-3741","authenticated-orcid":false,"given":"Mingjia","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Computer Science and the Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanxi","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6374-1429","authenticated-orcid":false,"given":"Yanan","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computer Science and the Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3956-3348","authenticated-orcid":false,"given":"Qing","family":"Ye","sequence":"additional","affiliation":[{"name":"College of Computer Science and the Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6551-3884","authenticated-orcid":false,"given":"Jiancheng","family":"Lv","sequence":"additional","affiliation":[{"name":"College of Computer Science and the Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1016\/j.cie.2020.106854"},{"key":"ref3","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Dean"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1145\/3320060"},{"key":"ref5","first-page":"1","article-title":"Prior: Personalized prior for reactivating the information overlooked in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shi"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1016\/j.ins.2024.120582"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TNNLS.2019.2944481"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/TPDS.2021.3090331"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1561\/2200000083"},{"key":"ref10","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICME57554.2024.10687740"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/TSMC.2024.3389672"},{"issue":"120","key":"ref13","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","first-page":"374","article-title":"Towards federated learning at scale: System design","volume-title":"Proc. Mach. Learn. Syst. (MLSys)","volume":"1","author":"Bonawitz"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2015-354"},{"key":"ref16","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"Lin","year":"2017","journal-title":"arXiv:1712.01887"},{"key":"ref17","first-page":"1","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wangni"},{"key":"ref18","first-page":"1","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref19","first-page":"560","article-title":"SignSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Bernstein"},{"key":"ref20","first-page":"3252","article-title":"Error feedback fixes SignSGD and other gradient compression schemes","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Karimireddy"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref22","article-title":"Federated learning via synthetic data","author":"Goetz","year":"2020","journal-title":"arXiv:2008.04489"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/JIOT.2021.3073112"},{"key":"ref24","article-title":"FedSynth: Gradient compression via synthetic data in federated learning","author":"Hu","year":"2022","journal-title":"arXiv:2204.01273"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.18653\/v1\/D17-1045"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1609\/aaai.v38i14.29454"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1137\/16M1080173"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"ref29","first-page":"4447","article-title":"Sparsified SGD with memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Stich"},{"key":"ref30","first-page":"1","article-title":"A theoretical study of dataset distillation","volume-title":"Proc. Workshop Math. Modern Mach. Learn. NeurIPS","author":"Izzo"},{"key":"ref31","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref32","first-page":"1","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Alistarh"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICCV51070.2023.00464"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1073\/pnas.2024789118"},{"key":"ref35","first-page":"8133","article-title":"Rethinking gradient sparsification as total error minimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sahu"},{"key":"ref36","first-page":"1","article-title":"Predicting parameters in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Denil"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.21437\/Interspeech.2014-274"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1038\/s41467-022-29763-x"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/TNNLS.2019.2953131"},{"key":"ref40","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1007\/s10462-021-09975-1"},{"key":"ref42","article-title":"IDLG: Improved deep leakage from gradients","author":"Zhao","year":"2020","journal-title":"arXiv:2001.02610"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/MNET.001.2300140"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref45","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1109\/IJCNN.2017.7966217"},{"year":"2009","author":"Krizhevsky","article-title":"Learning multiple layers of features from tiny images","key":"ref47"},{"key":"ref48","first-page":"1","article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref49","volume-title":"Maximum likelihood estimation of Dirichlet distribution parameters","volume":"76","author":"Huang","year":"2005"},{"key":"ref50","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1109\/ICDE53745.2022.00077"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.1109\/CVPR42600.2020.01044"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.5555\/3045118.3045167"},{"issue":"1","key":"ref55","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1109\/icassp49357.2023.10095399"},{"key":"ref57","first-page":"21394","article-title":"Personalized federated learning with Moreau envelopes","volume-title":"Proc. NIPS","volume":"33","author":"Dinh"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1109\/ICASSP48485.2024.10447282"},{"doi-asserted-by":"publisher","key":"ref59","DOI":"10.1609\/aaai.v35i12.17254"},{"key":"ref60","first-page":"24550","article-title":"Detached error feedback for distributed SGD with random sparsification","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Xu"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.20517\/ir.2021.02"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11114436\/10905051.pdf?arnumber=10905051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:37Z","timestamp":1764959977000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10905051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":61,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3539869","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}