{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:28:39Z","timestamp":1772908119258,"version":"3.50.1"},"reference-count":78,"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":[{"name":"Information Technology Research Center","award":["IITP-2025-RS-2023-00259991"],"award-info":[{"award-number":["IITP-2025-RS-2023-00259991"]}]},{"name":"Information Technology Research Center","award":["IITP-2025-RS-2020-II201787"],"award-info":[{"award-number":["IITP-2025-RS-2020-II201787"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tmc.2025.3549600","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T17:48:11Z","timestamp":1741628891000},"page":"6734-6746","source":"Crossref","is-referenced-by-count":5,"title":["NeFL: Nested Model Scaling for Federated Learning With System Heterogeneous Clients"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2138-8641","authenticated-orcid":false,"given":"Honggu","family":"Kang","sequence":"first","affiliation":[{"name":"Samsung Electronics, Suwon, South Korea"}]},{"given":"Seohyeon","family":"Cha","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, Austin, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4313-4669","authenticated-orcid":false,"given":"Jinwoo","family":"Shin","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"}]},{"given":"Jongmyeong","family":"Lee","sequence":"additional","affiliation":[{"name":"Beyless, Seongnam, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5508-3742","authenticated-orcid":false,"given":"Joonhyuk","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"}]}],"member":"263","reference":[{"key":"ref1","article-title":"NeFL project page","author":"Kang","year":"2024"},{"key":"ref2","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref3","first-page":"1","article-title":"Efficient split-mix federated learning for on-demand and in-situ customization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hong"},{"key":"ref4","first-page":"14068","article-title":"Group knowledge transfer: Federated learning of large CNNs at the edge","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.03.019"},{"key":"ref6","article-title":"Federated self-supervised learning for heterogeneous clients","author":"Makhija","year":"2022"},{"key":"ref7","first-page":"1","article-title":"Divergence-aware federated self-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhuang"},{"key":"ref8","article-title":"SSFL: Tackling label deficiency in federated learning via personalized self-supervision","author":"He","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref11","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref13","first-page":"12876","article-title":"FjORD: Fair and accurate federated learning under heterogeneous targets with ordered dropout","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Horv\u00e1th"},{"key":"ref14","first-page":"1","article-title":"HeteroFL: Computation and communication efficient federated learning for heterogeneous clients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Diao"},{"key":"ref15","first-page":"1","article-title":"DepthFL : Depthwise federated learning for heterogeneous clients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02350"},{"key":"ref17","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref18","first-page":"1","article-title":"On the importance and applicability of pre-training for federated learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00982"},{"key":"ref20","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref21","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref23","first-page":"129","article-title":"What is the state of neural network pruning","volume-title":"Proc. Conf. Mach. Learn. Syst.","author":"Blalock"},{"key":"ref24","first-page":"1","article-title":"A signal propagation perspective for pruning neural networks at initialization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref26","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","author":"Krishnamoorthi","year":"2018"},{"key":"ref27","article-title":"Split learning for health: Distributed deep learning without sharing raw patient data","author":"Vepakomma","year":"2018"},{"key":"ref28","first-page":"1","article-title":"Hypernetworks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ha"},{"key":"ref29","first-page":"6572","article-title":"Neural ordinary differential equations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref30","volume-title":"Solving Ordinary Differential Equations I Nonstiff problems","author":"Hairer","year":"2000"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29763-x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/9781108966559.019"},{"key":"ref33","article-title":"Data-free knowledge distillation for heterogeneous federated learning","author":"Zhu","year":"2021"},{"key":"ref34","first-page":"2351","article-title":"Ensemble distillation for robust model fusion in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref35","first-page":"1","article-title":"Towards model agnostic federated learning using knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Afonin"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3166101"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3247798"},{"key":"ref39","first-page":"8253","article-title":"FetchSGD: Communication-efficient federated learning with sketching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rothchild"},{"key":"ref40","first-page":"2350","article-title":"Federated learning with compression: Unified analysis and sharp guarantees","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Haddadpour"},{"key":"ref41","first-page":"25552","article-title":"Bitwidth heterogeneous federated learning with progressive weight dequantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yoon"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"ref43","article-title":"FedSplitX: Federated split learning for computationally-constrained heterogeneous clients","author":"Shin","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102141"},{"key":"ref45","article-title":"Think locally, act globally: Federated learning with local and global representations","author":"Liang","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00985"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3269062"},{"key":"ref48","first-page":"1","article-title":"On bridging generic and personalized federated learning for image classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref49","first-page":"9489","article-title":"Personalized federated learning using hypernetworks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shamsian"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref51","first-page":"1","article-title":"Multi-level residual networks from dynamical systems view","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/BF02288367"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref55","first-page":"1352","article-title":"Rezero is all you need: Fast convergence at large depth","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Bachlechner"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref58","first-page":"1","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref60","first-page":"1","article-title":"Federated learning based on dynamic regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Acar"},{"key":"ref61","first-page":"1","article-title":"When vision transformers outperform ResNets without pre-training or strong data augmentations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref62","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Conf. Mach. Learn. Syst.","author":"Li"},{"key":"ref63","first-page":"2488","article-title":"How does batch normalization help optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Santurkar"},{"key":"ref64","article-title":"Federated learning with personalization layers","author":"Arivazhagan","year":"2019"},{"key":"ref65","first-page":"1","article-title":"On the convergence of FedAvg on Non-IID data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref67","article-title":"CINIC-10 is not ImageNet or Cifar-10","author":"Darlow","year":"2018"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref69","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yurochkin"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/icde53745.2022.00077"},{"key":"ref71","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref73","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref74","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref75","first-page":"1","article-title":"Federated learning with matched averaging","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"ref77","article-title":"Federated learning with Non-IID data","author":"Zhao","year":"2018"},{"key":"ref78","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zoph"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01487-0"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11068893\/10918773.pdf?arnumber=10918773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T22:57:16Z","timestamp":1751929036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10918773\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":78,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3549600","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":[[2025,8]]}}}