{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T10:59:14Z","timestamp":1781607554845,"version":"3.54.5"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Start-up Research Grant of University of Macau","award":["SRG2022-00010-IOTSC"],"award-info":[{"award-number":["SRG2022-00010-IOTSC"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpds.2024.3480115","type":"journal-article","created":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T17:27:39Z","timestamp":1728926859000},"page":"2513-2526","source":"Crossref","is-referenced-by-count":8,"title":["Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splitting"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5220-1609","authenticated-orcid":false,"given":"Chunlin","family":"Tian","sequence":"first","affiliation":[{"name":"State Key Laboratory of IoTSC, University of Macau, Taipa, Macau SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2044-8289","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of IoTSC, University of Macau, Taipa, Macau SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5816-6837","authenticated-orcid":false,"given":"Kahou","family":"Tam","sequence":"additional","affiliation":[{"name":"State Key Laboratory of IoTSC, University of Macau, Taipa, Macau SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2422-1356","authenticated-orcid":false,"given":"Yebo","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of IoTSC, University of Macau, Taipa, Macau SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9480-0356","authenticated-orcid":false,"given":"Cheng-Zhong","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of IoTSC, University of Macau, Taipa, Macau SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u1ef3","year":"2016"},{"key":"ref2","article-title":"Machine learning model sizes and the parameter gap","author":"Villalobos","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3464298.3493394"},{"key":"ref4","article-title":"Low-memory neural network training: A technical report","author":"Sohoni","year":"2019"},{"key":"ref5","article-title":"Mobile RAM usage worldwide from 1Q-19 to 1Q-21 (in GB per device)","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3539765"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref11","article-title":"Mixed precision training","author":"Micikevicius","year":"2017"},{"key":"ref12","first-page":"22941","article-title":"On-device training under 256KB memory","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378530"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709284"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3298051"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682916"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iwqos61813.2024.10682916"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682959"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230529"},{"key":"ref21","first-page":"1","article-title":"Learn to select: Efficient cross-device federated learning via reinforcement learning","volume-title":"Proc. 1st Tiny Papers Track ICLR","author":"Tian"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682844"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/526"},{"key":"ref24","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref25","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538928"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3166101"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00047"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"ref33","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","author":"Mishra","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD53861.2021.00038"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS51746.2020.00017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15184-5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2320500"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3009406"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17219"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.038"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00049"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538917"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488723"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148586"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"ref47","article-title":"Server-side local gradient averaging and learning rate acceleration for scalable split learning","author":"Pal","year":"2021"},{"key":"ref48","article-title":"Detailed comparison of communication efficiency of split learning and federated learning","author":"Singh","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3176469"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3213411"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109380"},{"key":"ref52","first-page":"48211","article-title":"Ranking-based client imitation selection for efficient federated learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Tian"},{"key":"ref53","article-title":"Differentially private federated learning: A client level perspective","author":"Geyer","year":"2017"},{"key":"ref54","article-title":"A tutorial on Bayesian optimization","author":"Frazier","year":"2018"},{"key":"ref55","first-page":"9125","article-title":"Differentially private federated Bayesian optimization with distributed exploration","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3528535.3565244"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/72.286891"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"},{"key":"ref59","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref60","article-title":"Estimating a Dirichlet distribution","author":"Minka","year":"2000"},{"key":"ref61","article-title":"FedBE: Making Bayesian model ensemble applicable to federated learning","author":"Chen","year":"2020"},{"key":"ref62","article-title":"Federated learning based on dynamic regularization","author":"Acar","year":"2021"},{"key":"ref63","article-title":"Deep learning for Java","author":"Hamblen","year":"2024"},{"key":"ref64","article-title":"High voltage power monitor","author":"Solutions","year":"2024"},{"key":"ref65","article-title":"The MNIST database of handwritten digits.","author":"Lecun","year":"1998"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref67","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"Citeseer"},{"key":"ref68","article-title":"Shakespeare dataset","year":"2017"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref70","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref71","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref72","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":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392686"},{"key":"ref74","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":"ref75","first-page":"20296","article-title":"FedVS: Straggler-resilient and privacy-preserving vertical federated learning for split models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/10719599\/10716559.pdf?arnumber=10716559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T06:52:02Z","timestamp":1747119122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10716559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":75,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2024.3480115","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}