{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T03:52:59Z","timestamp":1772941979611,"version":"3.50.1"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key RD Program of China","award":["2022YFF0712100"],"award-info":[{"award-number":["2022YFF0712100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61921006"],"award-info":[{"award-number":["61921006"]}],"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":["62006118"],"award-info":[{"award-number":["62006118"]}],"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":["62276131"],"award-info":[{"award-number":["62276131"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tkde.2024.3390041","type":"journal-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T17:32:50Z","timestamp":1713979970000},"page":"6560-6573","source":"Crossref","is-referenced-by-count":11,"title":["MAP: Model Aggregation and Personalization in Federated Learning With Incomplete Classes"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9417-7971","authenticated-orcid":false,"given":"Xin-Chun","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, State Key Laboratory for Novel Software Technology, Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8662-6407","authenticated-orcid":false,"given":"Shaoming","family":"Song","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4263-5130","authenticated-orcid":false,"given":"Yinchuan","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7655-6919","authenticated-orcid":false,"given":"Bingshuai","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4335-5157","authenticated-orcid":false,"given":"Yunfeng","family":"Shao","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5245-3584","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3533-2078","authenticated-orcid":false,"given":"De-Chuan","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, State Key Laboratory for Novel Software Technology, Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","article-title":"Federated learning for emoji prediction in a mobile keyboard","author":"Ramaswamy","year":"2019","journal-title":"arXiv: 1906.04329"},{"key":"ref4","first-page":"1","article-title":"Parameter server for distributed machine learning","volume-title":"Proc. Big Learn. NeurIPS Workshop","author":"Li"},{"key":"ref5","first-page":"1232","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dean"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref7","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref8","first-page":"26293","article-title":"Personalized federated learning via variational Bayesian inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref9","article-title":"Aggregate or not? Exploring where to privatize in DNN based federated learning under different non-iid scenes","author":"Li","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2022.3222971"},{"key":"ref11","article-title":"Personalized federated learning via maximizing correlation with sparse and hierarchical extensions","author":"Li","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3271851"},{"key":"ref13","article-title":"FedCV: A federated learning framework for diverse computer vision tasks","author":"He","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00984"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.13"},{"key":"ref16","article-title":"Preliminary steps towards federated sentiment classification","author":"Li","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-558"},{"key":"ref18","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","author":"Li"},{"key":"ref19","article-title":"Federated learning with non-iid data","author":"Zhao","year":"2018"},{"key":"ref20","article-title":"Salvaging federated learning by local adaptation","author":"Yu","year":"2020"},{"key":"ref21","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Yurochkin"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/205"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17219"},{"key":"ref24","article-title":"Ensemble distillation for robust model fusion in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467254"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86486-6_36"},{"key":"ref28","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yosinski"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"ref30","volume-title":"Dataset Shift in Machine Learning","author":"Qui\u00f1onero-Candela","year":"2009"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00763"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00657"},{"key":"ref33","first-page":"1","article-title":"An agnostic approach to federated learning with class imbalance","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Shen"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00992"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330865"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3109131"},{"key":"ref37","first-page":"1","article-title":"On bridging generic and personalized federated learning for image classification","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref38","first-page":"1","article-title":"Communication-efficient on-device machine learning: Federated distillation and augmentation under non-iid private data","author":"Jeong","year":"2018","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref39","article-title":"Federated learning with unbiased gradient aggregation and controllable meta updating","author":"Yao","year":"2019"},{"key":"ref40","first-page":"6840","article-title":"Heterogeneous model reuse via optimizing multiparty multiclass margin","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref41","first-page":"1","article-title":"Federated learning based on dynamic regularization","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Acar"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2018.8698609"},{"key":"ref43","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref44","first-page":"1","article-title":"Adaptive federated optimization","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Reddi"},{"key":"ref45","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref46","first-page":"1","article-title":"Federated learning with matched averaging","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref47","first-page":"10946","article-title":"Federated learning with only positive labels","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_5"},{"key":"ref49","first-page":"3973","article-title":"FedBoost: A communication-efficient algorithm for federated learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Hamer"},{"key":"ref50","article-title":"Federated evaluation of on-device personalization","author":"Wang","year":"2019"},{"key":"ref51","first-page":"4424","article-title":"Federated multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Smith"},{"key":"ref52","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fallah"},{"key":"ref53","article-title":"Federated meta-learning for recommendation","author":"Chen","year":"2018"},{"key":"ref54","first-page":"473","article-title":"Personalized and private peer-to-peer machine learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Bellet"},{"key":"ref55","article-title":"Private federated learning with domain adaptation","author":"Peterson","year":"2019"},{"key":"ref56","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Collins"},{"key":"ref57","article-title":"Federated learning of a mixture of global and local models","author":"Hanzely","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"ref59","article-title":"Three approaches for personalization with applications to federated learning","author":"Mansour","year":"2020"},{"key":"ref60","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref61","first-page":"513","article-title":"A kernel method for the two-sample-problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gretton"},{"key":"ref62","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Long"},{"key":"ref63","first-page":"1","article-title":"Temperature check: Theory and practice for training models with softmax-cross-entropy losses","author":"Agarwala","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref64","article-title":"Rethinking softmax with cross-entropy: Neural network classifier as mutual information estimator","author":"Qin","year":"2019"},{"key":"ref65","first-page":"1","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Laine"},{"key":"ref66","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref67","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref68","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2012"},{"key":"ref69","article-title":"CINIC-10 is not ImageNet or CIFAR-10","author":"Darlow","year":"2018"},{"key":"ref70","article-title":"LEAF: A benchmark for federated settings","author":"Caldas","year":"2018"},{"key":"ref71","article-title":"The MNIST database of handwritten digits","author":"LeCun","year":"1998"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref74","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"ref77","article-title":"Personalized federated learning with moreau envelopes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dinh"},{"key":"ref78","first-page":"6357","article-title":"Ditto: Fair and robust federated learning through personalization","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref79","article-title":"FedMD: Heterogenous federated learning via model distillation","author":"Li","year":"2019"},{"key":"ref80","first-page":"17716","article-title":"Federated learning with partial model personalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pillutla"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10709365\/10508131.pdf?arnumber=10508131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T05:39:57Z","timestamp":1728452397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":80,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2024.3390041","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}