{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T19:13:25Z","timestamp":1782587605399,"version":"3.54.5"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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 Trans. on Mobile Comput."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tmc.2025.3581534","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T13:40:16Z","timestamp":1751290816000},"page":"12103-12120","source":"Crossref","is-referenced-by-count":4,"title":["Hierarchical and Heterogeneous Federated Learning via a Learning-on-Model Paradigm"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7661-6432","authenticated-orcid":false,"given":"Leming","family":"Shen","sequence":"first","affiliation":[{"name":"Department of Computing, Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5202-7892","authenticated-orcid":false,"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Cambridge, Cambridge, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8849-7477","authenticated-orcid":false,"given":"Kaiyan","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3096-687X","authenticated-orcid":false,"given":"Yuanqing","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Computing, Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5706-5177","authenticated-orcid":false,"given":"Xiao-Yong","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9003-8667","authenticated-orcid":false,"given":"Jianwei","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5064-1955","authenticated-orcid":false,"given":"Jinsong","family":"Han","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3302410"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3241770"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3467981"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3733841"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3603257"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3711875.3734561"},{"key":"ref7","article-title":"DeTrigger: A gradient-centric approach to backdoor attack mitigation in federated learning","author":"Lee","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3690705"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3643832.3661880"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.108468"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ton.2025.3539666"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3492140"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699326"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592524"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3697447"},{"key":"ref16","article-title":"FedMD: Heterogenous federated learning via model distillation","author":"Li","year":"2019"},{"key":"ref17","first-page":"1","article-title":"HeteroFL: Computation and communication efficient federated learning for heterogeneous clients","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Diao"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483278"},{"key":"ref19","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":"ref20","article-title":"Flower: A friendly federated learning research framework","author":"Beutel","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2025.104333"},{"key":"ref24","article-title":"FedRolex: Model-heterogeneous federated learning with rolling sub-model extraction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alam"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-0716-3195-9_22"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref28","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sundararajan"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00983"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568503"},{"key":"ref31","first-page":"1","article-title":"Towards model agnostic federated learning using knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Afonin"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467882"},{"key":"ref33","first-page":"23803","article-title":"Cross-entropy loss functions: Theoretical analysis and applications","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mao"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref35","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref36","first-page":"1","article-title":"Snapshot ensembles: Train 1, get M for free","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3214234"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3316645"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3554980"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485946"},{"key":"ref43","article-title":"Last layer re-training is sufficient for robustness to spurious correlations","author":"Kirichenko","year":"2022"},{"key":"ref44","article-title":"IDEAL: Query-efficient data-free learning from black-box models","author":"Zhang","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00033"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.05.003"},{"key":"ref48","article-title":"Reducing leakage in distributed deep learning for sensitive health data","author":"Vepakomma","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517017"},{"key":"ref51","article-title":"CINIC-10 is not ImageNet or CIFAR-10","author":"Darlow","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2021.3098818"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3443404"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00070"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485937"},{"key":"ref57","first-page":"1","article-title":"AutoIoT: LLM-driven automated natural language programming for AIoT applications","volume-title":"Proc. 31th Annu. Int. Conf. Mobile Comput. Netw.","author":"Shen"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3374046"},{"key":"ref59","first-page":"1","article-title":"Vortex EM wave-based rotation speed monitoring on commodity WiFi","volume":"34","author":"Leiyang","year":"2024","journal-title":"Chin. J. Electron."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3715014.3722064"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3625687.3625812"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2947024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485936"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3453142.3492909"},{"key":"ref65","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019"},{"key":"ref66","article-title":"Multi-task and transfer learning for federated learning applications","author":"Ke\u00e7eci","year":"2022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3437984.3458839"},{"key":"ref68","article-title":"8-bit approximations for parallelism in deep learning","author":"Dettmers","year":"2015"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485929"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3613297"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2171713"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3332637"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.5220\/0001770102730280"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3233\/IA-200075"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2988604"},{"key":"ref76","article-title":"Flower android example (TensorFlowLite)","author":"Beutel","year":"2023"},{"key":"ref77","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Sympos. Operat. Syst. Des. Implementation","author":"Abadi","year":"2016"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09825-6"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3228893"},{"key":"ref82","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yosinski"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3315451"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3390416"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00990"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00093"},{"key":"ref87","first-page":"1","article-title":"Rethinking the value of network pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.06.039"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11192678\/11059813.pdf?arnumber=11059813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T23:25:42Z","timestamp":1759793142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11059813\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":88,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3581534","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}