{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T20:42:07Z","timestamp":1785530527899,"version":"3.56.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council Discovery, LIEF, and Future Fellowship","doi-asserted-by":"publisher","award":["DP190101079"],"award-info":[{"award-number":["DP190101079"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council Discovery, LIEF, and Future Fellowship","doi-asserted-by":"publisher","award":["DP240102050"],"award-info":[{"award-number":["DP240102050"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council Discovery, LIEF, and Future Fellowship","doi-asserted-by":"publisher","award":["LE240100131"],"award-info":[{"award-number":["LE240100131"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council Discovery, LIEF, and Future Fellowship","doi-asserted-by":"publisher","award":["FT190100734"],"award-info":[{"award-number":["FT190100734"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council Discovery, LIEF, and Future Fellowship","doi-asserted-by":"publisher","award":["LP230201022"],"award-info":[{"award-number":["LP230201022"]}],"id":[{"id":"10.13039\/501100000923","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":[[2025,9]]},"DOI":"10.1109\/tnnls.2025.3562164","type":"journal-article","created":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T13:03:56Z","timestamp":1746536636000},"page":"16975-16989","source":"Crossref","is-referenced-by-count":27,"title":["FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1375-4664","authenticated-orcid":false,"given":"Hui","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalborg University, Aalborg, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangkai","family":"Wu","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology,, University of Technology Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7558-7200","authenticated-orcid":false,"given":"Xuhui","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-9429","authenticated-orcid":false,"given":"Longbing","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"7233","article-title":"Bayesian federated learning: A survey","volume-title":"Proc. IJCAI","author":"Cao"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00225"},{"key":"ref3","article-title":"GPT4Graph: Can large language models understand graph structured data ? An empirical evaluation and benchmarking","author":"Guo","year":"2023","journal-title":"arXiv:2305.15066"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3190359"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2022.3181504"},{"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.","volume":"54","author":"McMahan"},{"key":"ref8","first-page":"21394","article-title":"Personalized federated learning with Moreau envelopes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Dinh"},{"key":"ref9","first-page":"8392","article-title":"Personalized federated learning with Gaussian processes","volume-title":"Proc. NeurIPS","author":"Achituve"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539358"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498474"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2022.3194618"},{"key":"ref13","article-title":"On bridging generic and personalized federated learning for image classification","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref14","article-title":"Personalized federated learning with feature alignment and classifier collaboration","volume-title":"Proc. ICLR","author":"Xu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.14778\/3384345.3384353"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.14778\/3450980.3450987"},{"key":"ref17","article-title":"Federated learning with personalization layers","author":"Arivazhagan","year":"2019","journal-title":"arXiv:1912.00818"},{"key":"ref18","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Collins"},{"key":"ref19","article-title":"FedBABU: Towards enhanced representation for federated image classification","volume-title":"Proc. ICLR","author":"Oh"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref21","first-page":"4427","article-title":"Federated multi-task learning","volume-title":"Proc. NeurIPS","volume":"30","author":"Smith"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3224252"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250658"},{"key":"ref24","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume-title":"Proc. NeurIPS Conf.","volume":"33","author":"Fallah"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3269062"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3338867"},{"key":"ref27","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"arXiv:1606.06565"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3203977"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3294788"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3340741"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512201"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-3008-x"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-023-01177-9"},{"key":"ref35","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Welling"},{"key":"ref36","first-page":"2319","article-title":"Continuous-time edge modelling using non-parametric point processes","volume-title":"Proc. NeurIPS","volume":"34","author":"Fan"},{"key":"ref37","first-page":"3068","article-title":"Poisson-randomised DirBN: Large mutation is needed in Dirichlet belief networks","volume-title":"Proc. ICML","author":"Fan"},{"key":"ref38","first-page":"18723","article-title":"Function-space inference with sparse implicit processes","volume-title":"Proc. ICML","author":"Santana"},{"key":"ref39","first-page":"9603","article-title":"Free-form variational inference for Gaussian process state-space models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Fan"},{"key":"ref40","article-title":"Bayesian nonparametric space partitions: A survey","author":"Fan","year":"2020","journal-title":"arXiv:2002.11394"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103462"},{"key":"ref42","first-page":"1169","article-title":"Subspace inference for Bayesian deep learning","volume-title":"Proc. 35th Uncertainty Artif. Intell. Conf.","author":"Izmailov"},{"key":"ref43","first-page":"7694","article-title":"Do Bayesian neural networks need to be fully stochastic?","volume-title":"Proc. AISTATS","author":"Sharma"},{"key":"ref44","first-page":"2510","article-title":"Bayesian deep learning via subnetwork inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Daxberger"},{"key":"ref45","first-page":"17716","article-title":"Federated learning with partial model personalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pillutla"},{"key":"ref46","first-page":"8687","article-title":"FedPop: A Bayesian approach for personalised federated learning","volume-title":"Proc. NeurIPS","author":"Kotelevskii"},{"key":"ref47","first-page":"14003","article-title":"Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume-title":"Proc. NeurIPS","volume":"32","author":"Ovadia"},{"key":"ref48","article-title":"Deep ensembles: A loss landscape perspective","author":"Fort","year":"2019","journal-title":"arXiv:1912.02757"},{"key":"ref49","first-page":"15897","article-title":"On the expressiveness of approximate inference in Bayesian neural networks","volume-title":"Proc. NeurIPS","author":"Foong"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref51","article-title":"\u2019In-between\u2019uncertainty in Bayesian neural networks","volume-title":"Proc. ICML Workshop Uncertainty Robustness Deep Learn.","author":"Foong"},{"key":"ref52","first-page":"703","article-title":"Improving predictions of Bayesian neural nets via local linearization","volume-title":"Proc. AISTATS","author":"Immer"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"issue":"1","key":"ref54","first-page":"5776","article-title":"New insights and perspectives on the natural gradient method","volume":"21","author":"Martens","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref55","first-page":"2257","article-title":"Faster Wasserstein distance estimation with the sinkhorn divergence","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Chizat"},{"key":"ref56","first-page":"466","article-title":"Efficient variational inference for sparse deep learning with theoretical guarantee","volume-title":"Proc. NeurIPS","author":"Bai"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref58","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref59","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"ref60","first-page":"3","article-title":"Tiny ImageNet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"ref61","article-title":"FedRC: Tackling diverse distribution shifts challenge in federated learning by robust clustering","author":"Guo","year":"2023","journal-title":"arXiv:2301.12379"},{"key":"ref62","first-page":"37860","article-title":"Personalized federated learning under mixture of distributions","volume-title":"Proc. ICML","author":"Wu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00154"},{"key":"ref64","article-title":"Think locally, act globally: Federated learning with local and global representations","volume-title":"Proc. NeurIPS Workshop Federated Learn.","author":"Liang"},{"key":"ref65","first-page":"26293","article-title":"Personalized federated learning via variational Bayesian inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref66","article-title":"Bayesian personalized federated learning with shared and personalized uncertainty representations","author":"Chen","year":"2023","journal-title":"arXiv:2309.15499"},{"key":"ref67","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref68","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref69","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. 34th Intl. Conf. Mach. Learn.","author":"Guo"},{"key":"ref70","article-title":"FedBE: Making Bayesian model ensemble applicable to federated learning","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref71","article-title":"A Bayesian federated learning framework with online Laplace approximation","author":"Liu","year":"2021","journal-title":"arXiv:2102.01936"},{"key":"ref72","article-title":"Federated learning via posterior averaging: A new perspective and practical algorithms","volume-title":"Proc. ICLR","author":"Al-Shedivat"},{"key":"ref73","article-title":"Federated learning as variational inference: A scalable expectation propagation approach","volume-title":"Proc. ICLR","author":"Guo"},{"key":"ref74","first-page":"6459","article-title":"QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","volume":"151","author":"Vono"},{"key":"ref75","first-page":"9687","article-title":"Federated Bayesian optimization via Thompson sampling","volume-title":"Proc. NeurIPS","author":"Dai"},{"key":"ref76","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Yurochkin"},{"key":"ref77","article-title":"Federated learning with matched averaging","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199535255.001.0001"},{"key":"ref79","first-page":"1579","article-title":"On statistical optimality of variational Bayes","volume-title":"Proc. AISTATS","author":"Pati"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11151745\/10988883.pdf?arnumber=10988883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:24:49Z","timestamp":1757096689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10988883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":79,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3562164","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}