{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T13:21:16Z","timestamp":1771680076411,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T00:00:00Z","timestamp":1673740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T00:00:00Z","timestamp":1673740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T00:00:00Z","timestamp":1673740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2023,1,15]]},"DOI":"10.1109\/jiot.2022.3209865","type":"journal-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:53:19Z","timestamp":1664308399000},"page":"1517-1535","source":"Crossref","is-referenced-by-count":10,"title":["Federated Learning via Attentive Margin of Semantic Feature Representations"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2666-4342","authenticated-orcid":false,"given":"Umberto","family":"Michieli","sequence":"first","affiliation":[{"name":"Samsung R&D Institute U.K., Staines-upon-Thames, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0954-1201","authenticated-orcid":false,"given":"Marco","family":"Toldo","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute U.K., Staines-upon-Thames, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mete","family":"Ozay","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute U.K., Staines-upon-Thames, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2956615"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3118642"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3090430"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3030072"},{"key":"ref6","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"McMahan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3023905"},{"key":"ref9","first-page":"1","article-title":"Towards federated learning at scale: System design","volume-title":"Proc. Conf. Mach. Learn. Syst. (MLSys)","author":"Bonawitz"},{"key":"ref10","first-page":"1","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Conf. Mach. Learn. Syst. (MLSys)","author":"Li"},{"key":"ref11","article-title":"Adaptive federated optimization","author":"Reddi","year":"2020","journal-title":"arXiv:2003.00295"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5826"},{"key":"ref13","first-page":"4080","article-title":"Prototypical networks for few-shot learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Snell"},{"key":"ref14","article-title":"Prototype-based incremental few-shot semantic segmentation","author":"Cermelli","year":"2020","journal-title":"arXiv:2012.01415"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00140"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00117"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-004-1547-1"},{"key":"ref19","first-page":"462","article-title":"Margin analysis of the LVQ algorithm","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"2","author":"Crammer"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852464"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500890"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01170-8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_41"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3031390"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-013-1535-3"},{"key":"ref27","first-page":"423","article-title":"Generalized learning vector quantization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sato"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_5"},{"key":"ref29","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019","journal-title":"arXiv:1909.06335"},{"key":"ref30","first-page":"1","article-title":"Fair resource allocation in federated learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref31","first-page":"3973","article-title":"FedBoost: A communication-efficient algorithm for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Hamer"},{"key":"ref32","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Karimireddy"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9049023"},{"key":"ref34","first-page":"1000","article-title":"Communication-efficient distributed optimization using an approximate Newton-type method","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Shamir"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16960"},{"key":"ref36","first-page":"1","article-title":"Federated adversarial domain adaptation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Peng"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3387168.3387181"},{"key":"ref38","first-page":"1","article-title":"Abnormal client behavior detection in federated learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst. Workshops (NeurIPSW)","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00263"},{"key":"ref40","article-title":"Distilled one-shot federated learning","author":"Zhou","year":"2020","journal-title":"arXiv:2009.07999"},{"key":"ref41","article-title":"XOR mixup: Privacy-preserving data augmentation for one-shot federated learning","author":"Shin","year":"2020","journal-title":"arXiv:2006.05148"},{"key":"ref42","first-page":"2049","article-title":"Differentially-private clustering of easy instances","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Cohen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108746"},{"key":"ref44","article-title":"Federated learning with personalization layers","author":"Arivazhagan","year":"2019","journal-title":"arXiv:1912.00818"},{"key":"ref45","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Collins"},{"key":"ref46","article-title":"Multi-center federated learning","author":"Xie","year":"2021","journal-title":"arXiv:2108.08647"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00234"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00151"},{"key":"ref50","first-page":"1","article-title":"LEAF: A benchmark for federated settings","volume-title":"Proc. Workshop Federated Learn. Data Privacy Confidentiality","author":"Caldas"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966217"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref57","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref58","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Oper. Syst. Des. Implement. (OSDI)","author":"Abadi"},{"issue":"1","key":"ref59","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00925"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00350"},{"issue":"11","key":"ref62","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","first-page":"134","article-title":"For valid generalization, the size of the weights is more important than the size of the network","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Bartlett","year":"1996"},{"key":"ref64","first-page":"2124","article-title":"Multiclass boosting: Theory and algorithms","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Saberian","year":"2011"},{"issue":"137","key":"ref65","first-page":"1","article-title":"Multiclass boosting: Margins, codewords, losses, and algorithms","volume":"20","author":"Saberian","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","first-page":"479","article-title":"Margin analysis of the LVQ algorithm","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Crammer","year":"2002"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/026\/737400"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10007705\/09903844.pdf?arnumber=9903844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:38:36Z","timestamp":1705963116000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9903844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,15]]},"references-count":67,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2022.3209865","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,15]]}}}