{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T01:06:45Z","timestamp":1755220005090,"version":"3.43.0"},"reference-count":91,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222202","62232004"],"award-info":[{"award-number":["62222202","62232004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L223002"],"award-info":[{"award-number":["L223002"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"R&D Program of Beijing Municipal Science and Technology Commission","award":["Z231100007423014"],"award-info":[{"award-number":["Z231100007423014"]}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B18008"],"award-info":[{"award-number":["B18008"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BUPT innovation and entrepreneurship support program","award":["2025-YC-T014"],"award-info":[{"award-number":["2025-YC-T014"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tmc.2025.3553971","type":"journal-article","created":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T15:06:32Z","timestamp":1742828792000},"page":"8152-8166","source":"Crossref","is-referenced-by-count":0,"title":["ACL: Adaptive Edge-Cloud Collaborative Learning for Heterogeneous Devices With Unlabeled Local Data"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0262-3323","authenticated-orcid":false,"given":"Zhengyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"The State Key Laboratory of Networking and Switching Technology, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7337-9168","authenticated-orcid":false,"given":"Dong","family":"Zhao","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Networking and Switching Technology, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0759-787X","authenticated-orcid":false,"given":"Renhao","family":"Liu","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Networking and Switching Technology, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9381-2854","authenticated-orcid":false,"given":"Yuxing","family":"Yao","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Networking and Switching Technology, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Xiangyu","family":"Li","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Networking and Switching Technology, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7199-5047","authenticated-orcid":false,"given":"Huadong","family":"Ma","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Networking and Switching Technology, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"263","reference":[{"year":"2023","key":"ref1","article-title":"GPT-4 technical report"},{"article-title":"LLaMA: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref2"},{"key":"ref3","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00359"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592529"},{"key":"ref11","first-page":"1","article-title":"Once for all: Train one network and specialize it for efficient deployment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref14","first-page":"1","article-title":"Pruning filters for efficient ConvNets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref15","first-page":"38 087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592517"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01097"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448618"},{"key":"ref21","first-page":"119","article-title":"Ekya: Continuous learning of video analytics models on edge compute servers","volume-title":"Proc. 19th USENIX Symp. Netw. Syst. Des. Implementation","author":"Bhardwaj"},{"key":"ref22","first-page":"917","article-title":"RECL: Responsive resource-efficient continuous learning for video analytics","volume-title":"Proc. 20th USENIX Symp. Netw. Syst. Des. Implementation","author":"Khani"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3613297"},{"article-title":"DC-CCL: Device-cloud collaborative controlled learning for large vision models","year":"2023","author":"Ding","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363304"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467097"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3178211"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"article-title":"Federated fine-tuning of billion-sized language models across mobile devices","year":"2023","author":"Xu","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3613277"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592505"},{"key":"ref32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485946"},{"key":"ref34","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483278"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419188"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3447036"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2024.3403842"},{"key":"ref39","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref40","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li","year":"2020"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560519"},{"article-title":"Towards utilizing unlabeled data in federated learning: A survey and prospective","year":"2020","author":"Jin","key":"ref43"},{"key":"ref44","first-page":"17 871","article-title":"SemiFL: Semi-supervised federated learning for unlabeled clients with alternate training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Diao"},{"key":"ref45","first-page":"1","article-title":"Federated semi-supervised learning with inter-client consistency & disjoint learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jeong"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3550316"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3398202"},{"key":"ref50","first-page":"1","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref51","first-page":"1","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref52","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref53","first-page":"1","article-title":"Parameter-efficient multi-task and transfer learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sandler"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref56","first-page":"10 096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref57","first-page":"1","article-title":"Resource-aware heterogeneous federated learning using neural architecture search","volume-title":"Proc. 2021 IEEE Int. Conf. Big Data","author":"Yu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3432208"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671693"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref64","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref65","first-page":"1","article-title":"Rethinking the value of network pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3534586"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3534594"},{"key":"ref69","first-page":"11 285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cai"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01196"},{"key":"ref71","first-page":"4132","article-title":"Memory-efficient backpropagation through time","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gruslys"},{"article-title":"Training deep nets with sublinear memory cost","year":"2016","author":"Chen","key":"ref72"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.016"},{"article-title":"The Pascal visual object classes challenge 2012 (VOC2012) results","year":"2012","author":"Everingham","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref77","first-page":"1","article-title":"Maximum likelihood estimation of Dirichlet distribution parameters","volume":"18","author":"Huang","year":"2005","journal-title":"CMU Techn. Rep."},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref81","first-page":"2530","article-title":"CLAR: Contrastive learning of auditory representations","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Al-Tahan"},{"key":"ref82","first-page":"1","article-title":"Object-aware cropping for self-supervised learning","volume":"2022","author":"Mishra","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483249"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"ref85","first-page":"1","article-title":"Slimmable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430735"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360020"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430774"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485936"},{"key":"ref90","first-page":"1","article-title":"A DIRT-T approach to unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shu"},{"key":"ref91","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref92","first-page":"6028","article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00283"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11116789\/10937897.pdf?arnumber=10937897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:46:56Z","timestamp":1754588816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10937897\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":91,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3553971","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"type":"print","value":"1536-1233"},{"type":"electronic","value":"1558-0660"},{"type":"electronic","value":"2161-9875"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}