{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:31:18Z","timestamp":1780497078269,"version":"3.54.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tmc.2023.3316189","type":"journal-article","created":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T18:13:58Z","timestamp":1695060838000},"page":"6104-6115","source":"Crossref","is-referenced-by-count":8,"title":["Towards Resource-Efficient Edge AI: From Federated Learning to Semi-Supervised Model Personalization"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-670X","authenticated-orcid":false,"given":"Zhaofeng","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3416-8181","authenticated-orcid":false,"given":"Sheng","family":"Yue","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, 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":"College of Engineering, University of California, Davis, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2020.9055108"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155440"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00016"},{"key":"ref4","article-title":"Warm-start actor-critic: From approximation error to sub-optimality gap","author":"Wang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16638"},{"key":"ref6","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017","journal-title":"Artif. Intell. Statist."},{"key":"ref7","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3166101"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/dac18074.2021.9586241"},{"key":"ref11","article-title":"Distributed learning on heterogeneous resource-constrained devices","author":"Rapp","year":"2020"},{"key":"ref12","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref13","article-title":"Big self-supervised models are strong semi-supervised learners","author":"Chen","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.2995813"},{"key":"ref16","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155272"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA.1999.811269"},{"issue":"4","key":"ref19","first-page":"643","article-title":"Gradient methods for minimizing functionals","volume":"3","author":"Polyak","year":"1963","journal-title":"Zhurnal Vychislitel\u2019noi Matematiki i Matematicheskoi Fiziki"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3466772.3467038"},{"key":"ref21","article-title":"Personalized federated learning: A meta-learning approach","author":"Fallah","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00032"},{"key":"ref23","article-title":"Lets make block coordinate descent go fast: Faster greedy rules, message-passing, active-set complexity, and superlinear convergence","author":"Nutini","year":"2017"},{"key":"ref24","first-page":"1632","article-title":"Coordinate descent converges faster with the gauss-southwell rule than random selection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nutini"},{"key":"ref25","article-title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","author":"Zhang","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3143259"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref29","article-title":"MNIST handwritten digit database","author":"LeCun","year":"1998"},{"key":"ref30","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref31","first-page":"19","article-title":"Oort: Efficient federated learning via guided participant selection","volume-title":"Proc. 15th USENIX Symp. Operating Syst. Des. Implementation","author":"Lai"},{"key":"ref32","first-page":"10092","article-title":"Parameterized knowledge transfer for personalized federated learning","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref33","first-page":"9489","article-title":"Personalized federated learning using hypernetworks","volume-title":"Proc. Int. Conf. on Mach. Learn.","author":"Shamsian"},{"key":"ref34","first-page":"19332","article-title":"Federated learning from pre-trained models: A contrastive learning approach","volume":"35","author":"Tan","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","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":"Horvath"},{"key":"ref37","article-title":"Distributed learning of deep neural networks using independent subnet training","author":"Yuan","year":"2019"},{"key":"ref38","article-title":"ResIST: Layer-wise decomposition of resnets for distributed training","author":"Dun","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2020.3031503"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3015671"},{"key":"ref41","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. NeurIPS","author":"Grandvalet"},{"key":"ref42","article-title":"Theoretical analysis of self-training with deep networks on unlabeled data","author":"Wei","year":"2020"},{"key":"ref43","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","author":"Sohn","year":"2020"},{"key":"ref44","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Workshop Challenges Representation Learn.","author":"Lee"},{"key":"ref45","article-title":"Unsupervised data augmentation for consistency training","author":"Xie","year":"2019"},{"key":"ref46","first-page":"10738","article-title":"Self-tuning for data-efficient deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/72.248452"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(96)83696-3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/72.80236"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2986803"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7755\/10491282\/10254288-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7755\/10491282\/10254288.pdf?arnumber=10254288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T20:00:40Z","timestamp":1712692840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10254288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":50,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2023.3316189","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":[[2024,5]]}}}