{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:54:49Z","timestamp":1782575689616,"version":"3.54.5"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Information Technology Research Center"},{"name":"Korea Government","award":["IITP-2026-RS-2023-00259991"],"award-info":[{"award-number":["IITP-2026-RS-2023-00259991"]}]},{"name":"Korea Government","award":["IITP-2026-RS-2020-II201787"],"award-info":[{"award-number":["IITP-2026-RS-2020-II201787"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tmc.2025.3592483","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T17:57:58Z","timestamp":1753379878000},"page":"4493-4505","source":"Crossref","is-referenced-by-count":4,"title":["GeFL: Model-Agnostic Federated Learning With Generative Models"],"prefix":"10.1109","volume":"25","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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7080-2217","authenticated-orcid":false,"given":"Seohyeon","family":"Cha","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GeFL 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","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3549600"},{"key":"ref4","first-page":"1","article-title":"Towards model agnostic federated learning using knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Afonin"},{"key":"ref5","article-title":"Gemini: A family of highly capable multimodal models","year":"2023"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref7","article-title":"Machine learning model sizes and the parameter gap","author":"Villalobos","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3596907"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3075439"},{"key":"ref10","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","author":"Li"},{"key":"ref11","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":"ref12","first-page":"1","article-title":"DepthFL: Depthwise federated learning for heterogeneous clients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00990"},{"key":"ref15","article-title":"FedMD: Heterogenous federated learning via model distillation","author":"Li","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611781"},{"key":"ref17","first-page":"2672","article-title":"Generative adversarial networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Goodfellow"},{"key":"ref18","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2022"},{"key":"ref19","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref20","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref21","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/9781108966559.019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29763-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04431-1"},{"key":"ref25","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":"ref26","article-title":"Think locally, act globally: Federated learning with local and global representations","author":"Liang","year":"2020"},{"key":"ref27","article-title":"Federated mutual learning","author":"Shen","year":"2020"},{"key":"ref28","article-title":"Towards personalized federated learning via heterogeneous model reassembly","author":"Wang","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00381"},{"key":"ref30","article-title":"Communication-efficient on-device machine learning: Federated distillation and augmentation under non-IID private data","author":"Jeong","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/324"},{"key":"ref32","article-title":"FedGAN: Federated generative adversarial networks for distributed data","author":"Rasouli","year":"2020"},{"key":"ref33","first-page":"12878","article-title":"Data-free knowledge distillation for heterogeneous federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00993"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref37","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref39","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref40","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26330"},{"key":"ref42","first-page":"1","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Radford"},{"key":"ref43","first-page":"2352","article-title":"Variational autoencoder for deep learning of images, labels and captions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pu"},{"key":"ref44","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref45","first-page":"1","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS 2021 Workshop Deep Generative Models Downstream Appl.","author":"Ho"},{"key":"ref46","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref47","first-page":"12247","article-title":"Classification accuracy score for conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ravuri"},{"key":"ref48","first-page":"1","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref50","first-page":"1","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref51","article-title":"AutoAugment: Learning augmentation policies from data","author":"Cubuk","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref53","first-page":"16937","article-title":"Inverting gradients-how easy is it to break privacy in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Geiping"},{"key":"ref54","first-page":"27916","article-title":"On memorization in probabilistic deep generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"van den Burg"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01153"},{"key":"ref57","first-page":"10223","article-title":"Privacy assessment on reconstructed images: Are existing evaluation metrics faithful to human perception","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2019-0067"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref60","article-title":"Differentially private generative adversarial network","author":"Xie","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref62","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.522"},{"key":"ref65","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545073"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892815"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref70","article-title":"CIFAR-10 (Canadian Institute for Advanced Research)","author":"Krizhevsky","year":"2009"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00705"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2098"},{"key":"ref73","first-page":"1","article-title":"Synthetic data from diffusion models improves ImageNet classification","author":"Azizi","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_14"},{"key":"ref75","first-page":"27315","article-title":"Regularizing neural networks with meta-learning generative models","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Yamaguchi"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3138848"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11423852\/11095422.pdf?arnumber=11095422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T06:17:21Z","timestamp":1780985841000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11095422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":76,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3592483","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":[[2026,4]]}}}