{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T17:02:44Z","timestamp":1783184564347,"version":"3.54.6"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","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":"National Key Research and Development Program of China","award":["2022YFB2703303"],"award-info":[{"award-number":["2022YFB2703303"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62432004"],"award-info":[{"award-number":["62432004"]}],"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":["62411540034"],"award-info":[{"award-number":["62411540034"]}],"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":["62402267"],"award-info":[{"award-number":["62402267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Guoqiang Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/ton.2025.3548277","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T13:35:44Z","timestamp":1744724144000},"page":"1870-1885","source":"Crossref","is-referenced-by-count":2,"title":["AugFL: Augmenting Federated Learning With Pretrained Models"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3416-8181","authenticated-orcid":false,"given":"Sheng","family":"Yue","sequence":"first","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zerui","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3010-3812","authenticated-orcid":false,"given":"Yongheng","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2782-183X","authenticated-orcid":false,"given":"Ju","family":"Ren","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6717-461X","authenticated-orcid":false,"given":"Yaoxue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3840-1753","authenticated-orcid":false,"given":"Junshan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California at Davis, Davis, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3466772.3467038"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref5","first-page":"374","article-title":"Towards federated learning at scale: System design","volume-title":"Proc. Int. Conf. Mach. Learn. Syst.","volume":"1","author":"Bonawitz"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3035770"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3075439"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2021.07.008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3081560"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3637868"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3363916"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.004.2100182"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.031"},{"key":"ref15","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Brown"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793591"},{"key":"ref17","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref18","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"issue":"240","key":"ref19","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref20","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref21","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.425"},{"key":"ref23","article-title":"Privately customizing prefinetuning to better match user data in federated learning","volume-title":"Proc. Int. Workshop Pitfalls Ltd. Data Comput. Trustworthy ML ICLR","author":"Hou"},{"key":"ref24","article-title":"Selective pre-training for private fine-tuning","author":"Yu","year":"2023","journal-title":"arXiv:2305.13865"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.29012\/jpc.880","article-title":"Differentially private fine-tuning of language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yu"},{"key":"ref26","first-page":"29468","article-title":"Differentially private model compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Mireshghallah"},{"key":"ref27","article-title":"Backdoor threats from compromised foundation models to federated learning","volume-title":"Proc. Int. Workshop Federated Learn. Age Found. Models Conjunct NeurIPS","author":"Li"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.59"},{"key":"ref29","article-title":"Mobile foundation model as firmware","author":"Yuan","year":"2023","journal-title":"arXiv:2308.14363"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3742788"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00269"},{"key":"ref33","article-title":"Privacy safe representation learning via frequency filtering encoder","author":"Jeong","year":"2022","journal-title":"arXiv:2208.02482"},{"key":"ref34","volume-title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","year":"2024"},{"key":"ref35","article-title":"ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools","author":"Glm","year":"2024","journal-title":"arXiv:2406.12793"},{"key":"ref36","article-title":"Mooncake: A KVCache-centric disaggregated architecture for LLM serving","author":"Qin","year":"2024","journal-title":"arXiv:2407.00079"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195956"},{"key":"ref38","article-title":"FATE-LLM: A industrial grade federated learning framework for large language models","author":"Fan","year":"2023","journal-title":"arXiv:2310.10049"},{"key":"ref39","article-title":"Offsite-tuning: Transfer learning without full model","author":"Xiao","year":"2023","journal-title":"arXiv:2302.04870"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1137\/140990309"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-018-0757-z"},{"issue":"38","key":"ref42","first-page":"1","article-title":"Convergence for nonconvex ADMM, with applications to CT imaging","volume":"25","author":"Barber","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00032"},{"key":"ref44","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Fallah"},{"key":"ref45","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u00fd","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref46","article-title":"Where to begin? On the impact of pre-training and initialization in federated learning","author":"Nguyen","year":"2022","journal-title":"arXiv:2206.15387"},{"key":"ref47","first-page":"19332","article-title":"Federated learning from pre-trained models: A contrastive learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Tan"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01151"},{"key":"ref49","first-page":"14068","article-title":"Group knowledge transfer: Federated learning of large CNNs at the edge","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"He"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"ref51","article-title":"Communication-efficient on-device machine learning: Federated distillation and augmentation under non-IID private data","author":"Jeong","year":"2018","journal-title":"arXiv:1811.11479"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"key":"ref53","article-title":"Federated learning with personalization layers","author":"Arivazhagan","year":"2019","journal-title":"arXiv:1912.00818"},{"key":"ref54","first-page":"4427","article-title":"Federated multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"30","author":"Smith"},{"key":"ref55","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref56","article-title":"Federated meta-learning with fast convergence and efficient communication","author":"Chen","year":"2018","journal-title":"arXiv:1802.07876"},{"key":"ref57","article-title":"Improving federated learning personalization via model agnostic meta learning","author":"Jiang","year":"2019","journal-title":"arXiv:1909.12488"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2015.2476198"},{"key":"ref59","article-title":"Convergence of Bregman alternating direction method with multipliers for nonconvex composite problems","author":"Wang","year":"2014","journal-title":"arXiv:1410.8625"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-017-9367-6"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-018-0034-y"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s00211-016-0842-x"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1137\/19M1298007"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"issue":"330","key":"ref65","first-page":"23","article-title":"Transfer learning from pre-trained models","volume":"10","author":"Marcelino","year":"2018","journal-title":"Towards Data Sci."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16969"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3115952"},{"key":"ref72","first-page":"1082","article-title":"On the convergence theory of gradient-based model-agnostic meta-learning algorithms","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","volume":"108","author":"Fallah"},{"key":"ref73","article-title":"Meta continual learning via dynamic programming","author":"Krishnan","year":"2020","journal-title":"arXiv:2008.02219"},{"key":"ref74","article-title":"Contrastive representation distillation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Tian"},{"key":"ref75","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref76","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966217"},{"key":"ref78","article-title":"A downsampled variant of ImageNet as an alternative to the CIFAR datasets","author":"Chrabaszcz","year":"2017","journal-title":"arXiv:1707.08819"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599345"},{"key":"ref81","volume-title":"ResNet\u2014Torchvision Main Documentation","year":"2025"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3490035.3490300"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11131549\/10964341.pdf?arnumber=10964341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:52:04Z","timestamp":1755910324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10964341\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":82,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3548277","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}