{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:35:19Z","timestamp":1782833719812,"version":"3.54.5"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["2023YFE0209100"],"award-info":[{"award-number":["2023YFE0209100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272046"],"award-info":[{"award-number":["62272046"]}],"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":["62132019"],"award-info":[{"award-number":["62132019"]}],"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":["61872337"],"award-info":[{"award-number":["61872337"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006579","name":"Ministry of Industry and Information Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["CEIEC-20240"],"award-info":[{"award-number":["CEIEC-20240"]}],"id":[{"id":"10.13039\/501100006579","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tmc.2024.3504859","type":"journal-article","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T19:13:54Z","timestamp":1732302834000},"page":"2690-2707","source":"Crossref","is-referenced-by-count":6,"title":["EdgeTA: Neuron-Grained Scaling of Foundation Models in Edge-Side Retraining"],"prefix":"10.1109","volume":"24","author":[{"given":"Qinglong","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6894-1921","authenticated-orcid":false,"given":"Rui","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0252-329X","authenticated-orcid":false,"given":"Chi Harold","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0181-8379","authenticated-orcid":false,"given":"Guoren","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9831-2202","authenticated-orcid":false,"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4228-6735","authenticated-orcid":false,"given":"Lydia Y.","family":"Chen","sequence":"additional","affiliation":[{"name":"TU Delft, Delft, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3052975"},{"key":"ref5","first-page":"371","article-title":"NeuOS: A latency-predictable multi-dimensional optimization framework for DNN-driven autonomous systems","volume-title":"Proc. USENIX Annu. Techn. Conf.","author":"Bateni"},{"key":"ref6","first-page":"119","article-title":"Ekya: Continuous learning of video analytics models on edge compute servers","volume-title":"Proc. Symp. Netw. Syst. Des. Implementation","author":"Bhardwaj"},{"key":"ref7","article-title":"GPT-Neo: Large scale autoregressive language modeling with mesh-tensorflow","author":"Black","year":"2021"},{"key":"ref8","first-page":"119","article-title":"Adapting to continuously shifting domains","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Bobu"},{"key":"ref9","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref10","article-title":"FreezeOut: Accelerate training by progressively freezing layers","author":"Brock","year":"2017"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref12","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":"ref13","first-page":"1","article-title":"Efficient lifelong learning with A-GEM","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chaudhry"},{"key":"ref14","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3447085"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.581"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref19","first-page":"30318","article-title":"GPT3.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dettmers"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref21","first-page":"664","article-title":"A winning hand: Compressing deep networks can improve out-of-distribution robustness","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Diffenderfer"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00508"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1341531.1341561"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3172402"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/0047-259X(82)90077-X"},{"key":"ref27","first-page":"1","article-title":"Source-free adaptation to measurement shift via bottom-up feature restoration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eastwood"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533229"},{"key":"ref30","first-page":"1","article-title":"Dynamic channel pruning: Feature boosting and suppression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gao"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref32","article-title":"On the domain adaptation and generalization of pretrained language models: A survey","author":"Guo","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483249"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"key":"ref35","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Han"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref37","first-page":"1","article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref39","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref40","first-page":"9782","article-title":"DynaBERT: Dynamic BERT with adaptive width and depth","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref41","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014073"},{"key":"ref44","first-page":"1","article-title":"Multi-scale dense convolutional networks for efficient prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang"},{"key":"ref45","first-page":"721","article-title":"Elastic resource sharing for distributed deep learning","volume-title":"Proc. Symp. Netw. Syst. Des. Implementation","author":"Hwang"},{"key":"ref46","first-page":"29","article-title":"Mainstream: Dynamic stem-sharing for multi-tenant video processing","volume-title":"Proc. USENIX Annu. Techn. Conf.","author":"Jiang"},{"key":"ref47","first-page":"3647","article-title":"Continual learning with node-importance based adaptive group sparse regularization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jung"},{"issue":"11","key":"ref48","first-page":"1586","article-title":"No-Scope: Optimizing neural network queries over video at scale","volume-title":"Proc. VLDB Endowment","volume":"10","author":"Kang"},{"key":"ref49","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref51","first-page":"917","article-title":"RECL: Responsive resource-efficient continuous learning for video analytics","volume-title":"Proc. Symp. Netw. Syst. Des. Implementation","author":"Khani"},{"key":"ref52","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref53","first-page":"1","article-title":"Compression of deep convolutional neural networks for fast and low power mobile applications","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref55","first-page":"3478","article-title":"Decentralized stochastic optimization and gossip algorithms with compressed communication","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koloskova"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3229556.3229562"},{"key":"ref57","first-page":"1","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref58","first-page":"3049","article-title":"Asynchronous decentralized parallel stochastic gradient descent","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lian"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref61","first-page":"1291","article-title":"Automated rule selection for aspect extraction in opinion mining","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Liu"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3218724"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CogMI48466.2019.00035"},{"key":"ref64","first-page":"1","article-title":"A gradient flow framework for analyzing network pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"SinghLubana"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3081333.3081359"},{"key":"ref66","first-page":"1","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mehta"},{"key":"ref67","first-page":"579","article-title":"Looking beyond GPUs for DNN scheduling on multi-tenant clusters","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Mohan"},{"key":"ref68","first-page":"6829","article-title":"Asynchronous decentralized SGD with quantized and local updates","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nadiradze"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref70","first-page":"1","article-title":"Towards stable test-time adaptation in dynamic wild world","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Niu"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00839"},{"key":"ref72","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref73","first-page":"17284","article-title":"Formalizing the generalization-forgetting trade-off in continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Raghavan"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.300"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"ref77","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv: 1910.01108"},{"key":"ref78","article-title":"Foundation models in brief: A historical, socio-technical focus","author":"Schneider","year":"2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00524"},{"key":"ref80","first-page":"4552","article-title":"Real-time video inference on edge devices via adaptive model streaming","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Shirkoohi"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695964"},{"key":"ref82","first-page":"19523","article-title":"Beyond neural scaling laws: Beating power law scaling via data pruning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sorscher"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01423"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1021"},{"key":"ref86","article-title":"Distilling task-specific knowledge from BERT into simple neural networks","author":"Tang","year":"2019"},{"key":"ref87","article-title":"CONDA: Continual unsupervised domain adaptation","author":"Taufique","year":"2021"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.226"},{"key":"ref90","first-page":"1","article-title":"Contrastive representation distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tian"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref92","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592529"},{"key":"ref94","article-title":"HuggingFace\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.273"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00221"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460982"},{"key":"ref98","article-title":"Towards efficient task-driven model reprogramming with foundation models","author":"Xu","year":"2023"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3625687.3625793"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2976762"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref102","first-page":"1","article-title":"Slimmable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21423"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00288"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3223944"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3189186"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544224"},{"key":"ref108","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zoph"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/10916419\/10764793.pdf?arnumber=10764793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T19:44:14Z","timestamp":1741376654000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10764793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":106,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2024.3504859","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":[[2025,4]]}}}