{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:29:54Z","timestamp":1775521794205,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T00:00:00Z","timestamp":1686268800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T00:00:00Z","timestamp":1686268800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2017YFA0700300"],"award-info":[{"award-number":["2017YFA0700300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903356"],"award-info":[{"award-number":["61903356"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Liaoning Natural Science Foundation","doi-asserted-by":"crossref","award":["2021-MS-030"],"award-info":[{"award-number":["2021-MS-030"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100005047","name":"Liaoning Natural Science Foundation","doi-asserted-by":"crossref","award":["2022JH6\/100100013"],"award-info":[{"award-number":["2022JH6\/100100013"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Independent project of State Key Laboratory of Robotics","award":["2022-Z03"],"award-info":[{"award-number":["2022-Z03"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2023,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Federated learning is an effective solution for edge training, but the limited bandwidth and insufficient computing resources of edge devices restrict its deployment. Different from existing methods that only consider communication efficiency such as quantization and sparsification, this paper proposes an efficient federated training framework based on model pruning to simultaneously address the problem of insufficient computing and communication resources. First, the framework dynamically selects neurons or convolution kernels before the global model release, pruning a current optimal subnet and then issues the compressed model to each client for training. Then, we develop a new parameter aggregation update scheme, which provides training opportunities for global model parameters and maintains the complete model structure through model reconstruction and parameter reuse, reducing the error caused by pruning. Finally, extensive experiments show that our proposed framework achieves superior performance on both IID and non-IID datasets, which reduces upstream and downstream communication while maintaining the accuracy of the global model and reducing client computing costs. For example, with accuracy exceeding the baseline, computation is reduced by 72.27% and memory usage is reduced by 72.17% for MNIST\/FC; and computation is reduced by 63.39% and memory usage is reduced by 59.78% for CIFAR10\/VGG16.<\/jats:p>","DOI":"10.1007\/s40747-023-01120-5","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T18:03:09Z","timestamp":1686333789000},"page":"6999-7013","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Efficient federated learning on resource-constrained edge devices based on model pruning"],"prefix":"10.1007","volume":"9","author":[{"given":"Tingting","family":"Wu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8392-1777","authenticated-orcid":false,"given":"Chunhe","family":"Song","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Zeng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,9]]},"reference":[{"issue":"6","key":"1120_CR1","doi-asserted-by":"publisher","first-page":"4589","DOI":"10.1109\/JIOT.2018.2867333","volume":"5","author":"AL Diedrichs","year":"2018","unstructured":"Diedrichs AL, Bromberg F, Dujovne D, Brun-Laguna K, Watteyne T (2018) Prediction of frost events using machine learning and iot sensing devices. IEEE Internet Things J 5(6):4589\u20134597","journal-title":"IEEE Internet Things J"},{"issue":"1","key":"1120_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JIOT.2017.2773600","volume":"5","author":"OB Sezer","year":"2017","unstructured":"Sezer OB, Dogdu E, Ozbayoglu AM (2017) Context-aware computing, learning, and big data in internet of things: a survey. IEEE Internet Things J 5(1):1\u201327","journal-title":"IEEE Internet Things J"},{"key":"1120_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107338","volume":"229","author":"Z Xiao","year":"2021","unstructured":"Xiao Z, Xu X, Xing H, Song F, Wang X, Zhao B (2021) A federated learning system with enhanced feature extraction for human activity recognition. Knowl-Based Syst 229:107338. https:\/\/doi.org\/10.1016\/j.knosys.2021.107338","journal-title":"Knowl-Based Syst"},{"issue":"2","key":"1120_CR4","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/s40747-020-00247-z","volume":"7","author":"H Zhu","year":"2021","unstructured":"Zhu H, Zhang H, Jin Y (2021) From federated learning to federated neural architecture search: a survey. Compl Intell Syst 7(2):639\u2013657","journal-title":"Compl Intell Syst"},{"key":"1120_CR5","doi-asserted-by":"publisher","unstructured":"Lin R, Xiao Y, Yang T-J, Zhao D, Xiong L, Motta G, Beaufays F (2022) Federated pruning: improving neural network efficiency with federated learning, vol 2022. Incheon, Korea, Republic of, pp 1701\u20131705. In: Automatic speech recognition; client devices; deep learning; federated learning; federated pruning; large amounts; network efficiency; neural-networks; recognition models; speech data. https:\/\/doi.org\/10.21437\/Interspeech.2022-10787","DOI":"10.21437\/Interspeech.2022-10787"},{"key":"1120_CR6","unstructured":"McMahan B, Moore E, Ramage D, Hampson S, Arcas BA (2017) Communication-efficient learning of deep networks from decentralized data. In: Artificial intelligence and statistics, PMLR, pp 1273\u20131282"},{"key":"1120_CR7","unstructured":"You Z, Yan K, Ye J, Ma M, Wang P (2019) Gate decorator: Global filter pruning method for accelerating deep convolutional neural networks, vol 32. Vancouver, BC, Canada, p. Baseline models; iterative pruning; pruning algorithms; pruning methods; scaling factors; special operations; state of the art; Taylor expansions"},{"key":"1120_CR8","doi-asserted-by":"crossref","unstructured":"Lin M, Ji R, Wang Y, Zhang Y, Zhang B, Tian Y, Shao L (2020) Hrank: filter pruning using high-rank feature map. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1529\u20131538","DOI":"10.1109\/CVPR42600.2020.00160"},{"issue":"1","key":"1120_CR9","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1109\/TCOMM.2021.3124961","volume":"70","author":"S Liu","year":"2022","unstructured":"Liu S, Yu G, Yin R, Yuan J, Shen L, Liu C (2022) Joint model pruning and device selection for communication-efficient federated edge learning. IEEE Trans Commun 70(1):231\u2013244. https:\/\/doi.org\/10.1109\/TCOMM.2021.3124961","journal-title":"IEEE Trans Commun"},{"key":"1120_CR10","unstructured":"Zhou, G., Xu, K., Li, Q., Liu, Y., & Zhao, Y. (2021) AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning. arXiv preprint arXiv:2106.14126"},{"key":"1120_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2022.3166101","volume":"2022","author":"Y Jiang","year":"2022","unstructured":"Jiang Y, Wang S, Valls V, Ko BJ, Lee W-H, Leung KK, Tassiulas L (2022) Model pruning enables efficient federated learning on edge devices. IEEE Trans Neural Netw Learn Syst 2022:1\u201313. https:\/\/doi.org\/10.1109\/TNNLS.2022.3166101","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1120_CR12","doi-asserted-by":"crossref","unstructured":"Lin R, Xiao Y, Yang T-J, Zhao D, Xiong L, Motta G, Beaufays F (2022) Federated pruning: improving neural network efficiency with federated learning. arXiv:2209.06359","DOI":"10.21437\/Interspeech.2022-10787"},{"key":"1120_CR13","first-page":"177","volume":"1","author":"S Hanson","year":"1988","unstructured":"Hanson S, Pratt L (1988) Comparing biases for minimal network construction with back-propagation. Adv Neural Inf Process Syst 1:177\u2013185","journal-title":"Adv Neural Inf Process Syst"},{"key":"1120_CR14","unstructured":"Han S, Mao H, Dally WJ (2016) Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding, San Juan, Puerto rico. In: Complex neural networks; compression methods; dram memory; hardware resources; Huffman coding; loss of accuracy; mobile applications; storage requirements"},{"key":"1120_CR15","volume-title":"Pruning filters for efficient convnets","author":"H Li","year":"2017","unstructured":"Li H, Samet H, Kadav A, Durdanovic I, Graf HP (2017) Pruning filters for efficient convnets. Toulon, France"},{"key":"1120_CR16","unstructured":"Liu B, Wang M, Foroosh H, Tappen M, Pensky M (2015) Sparse convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 806\u2013814"},{"key":"1120_CR17","doi-asserted-by":"crossref","unstructured":"Liu Z, Li J, Shen Z, Huang G, Yan S, Zhang C (2017) Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE international conference on computer vision, pp 2736\u20132744","DOI":"10.1109\/ICCV.2017.298"},{"key":"1120_CR18","doi-asserted-by":"crossref","unstructured":"He Y, Zhang X, Sun J (2017) Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE international conference on computer vision, pp 1389\u20131397","DOI":"10.1109\/ICCV.2017.155"},{"key":"1120_CR19","unstructured":"Molchanov P, Tyree S, Karras T, Aila T, Kautz J (2017) Pruning convolutional neural networks for resource efficient inference, Toulon, France. In: Classification tasks; computationally efficient; convolutional kernel; gradient informations; Kernel weight; network parameters; resource-efficient; Taylor expansions"},{"key":"1120_CR20","unstructured":"Lee N, Ajanthan T, Torr PHS (2019) Snip: Single-shot network pruning based on connection sensitivity, New Orleans, LA, United states. In: Classification tasks; hyperparameters; iterative optimization; network pruning; new approaches; recurrent networks; reference network; sparse network"},{"key":"1120_CR21","doi-asserted-by":"crossref","unstructured":"He Y, Liu P, Wang Z, Hu Z, Yang Y (2019) Filter pruning via geometric median for deep convolutional neural networks acceleration. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4340\u20134349","DOI":"10.1109\/CVPR.2019.00447"},{"key":"1120_CR22","doi-asserted-by":"crossref","unstructured":"Guo S, Wang Y, Li Q, Yan J (2020) Dmcp: differentiable markov channel pruning for neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1539\u20131547","DOI":"10.1109\/CVPR42600.2020.00161"},{"key":"1120_CR23","first-page":"25","volume":"28","author":"S Han","year":"2015","unstructured":"Han S, Pool J, Tran J, Dally W (2015) Learning both weights and connections for efficient neural network. Adv Neural Inf Process Syst 28:25","journal-title":"Adv Neural Inf Process Syst"},{"issue":"8","key":"1120_CR24","doi-asserted-by":"publisher","first-page":"3594","DOI":"10.1109\/TCYB.2019.2933477","volume":"50","author":"Y He","year":"2019","unstructured":"He Y, Dong X, Kang G, Fu Y, Yan C, Yang Y (2019) Asymptotic soft filter pruning for deep convolutional neural networks. IEEE Trans Cybern 50(8):3594\u20133604","journal-title":"IEEE Trans Cybern"},{"key":"1120_CR25","doi-asserted-by":"crossref","unstructured":"Shen S, Li R, Zhao Z, Zhang H, Zhou Y (2021) Learning to prune in training via dynamic channel propagation. In: 2020 25th international conference on pattern recognition (ICPR), pp 939\u2013945, IEEE","DOI":"10.1109\/ICPR48806.2021.9412191"},{"key":"1120_CR26","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1016\/j.ins.2021.06.039","volume":"575","author":"N Tonellotto","year":"2021","unstructured":"Tonellotto N, Gotta A, Nardini FM, Gadler D, Silvestri F (2021) Neural network quantization in federated learning at the edge. Inf Sci 575:417\u2013436","journal-title":"Inf Sci"},{"key":"1120_CR27","unstructured":"Bernstein J, Wang Y-X, Azizzadenesheli K, Anandkumar A (2018) signsgd: compressed optimisation for non-convex problems. In: International conference on machine learning, pp 560\u2013569, PMLR"},{"issue":"9","key":"1120_CR28","doi-asserted-by":"publisher","first-page":"3400","DOI":"10.1109\/TNNLS.2019.2944481","volume":"31","author":"F Sattler","year":"2019","unstructured":"Sattler F, Wiedemann S, M\u00fcller K-R, Samek W (2019) Robust and communication-efficient federated learning from non-iid data. IEEE Trans Neural Netw Learn Syst 31(9):3400\u20133413","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1120_CR29","first-page":"2598","volume":"2020","author":"J Xu","year":"2020","unstructured":"Xu J, Du W, Jin Y, He W, Cheng R (2020) Ternary compression for communication-efficient federated learning. IEEE Trans Neural Netw Learn Syst 2020:2598","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1120_CR30","unstructured":"Wen W, Xu C, Yan F, Wu C, Wang Y, Chen Y, Li H (2017) Terngrad: ternary gradients to reduce communication in distributed deep learning, vol 2017. Long Beach, CA, United states, pp 1510\u20131520. In: Accuracy loss; communication time; data parallelism; layer-wise; network communications; performance model; source codes"},{"key":"1120_CR31","unstructured":"Zhang H, Li J, Kara K, Alistarh D, Liu J, Zhang C (2017) Zipml: training linear models with end-to-end low precision, and a little bit of deep learning. In: International conference on machine learning, pp 4035\u20134043, PMLR"},{"key":"1120_CR32","unstructured":"Wu J, Huang W, Huang J, Zhang T (2018) Error compensated quantized sgd and its applications to large-scale distributed optimization. In: International conference on machine learning, pp 5325\u20135333, PMLR"},{"key":"1120_CR33","doi-asserted-by":"publisher","first-page":"6101","DOI":"10.1109\/TSP.2020.3031073","volume":"68","author":"S Magn\u00fasson","year":"2020","unstructured":"Magn\u00fasson S, Shokri-Ghadikolaei H, Li N (2020) On maintaining linear convergence of distributed learning and optimization under limited communication. IEEE Trans Signal Process 68:6101\u20136116","journal-title":"IEEE Trans Signal Process"},{"key":"1120_CR34","unstructured":"Mishchenko K, Gorbunov E, Tak\u00e1\u010d M, Richt\u00e1rik P (2019) Distributed learning with compressed gradient differences. arXiv:1901.09269"},{"key":"1120_CR35","doi-asserted-by":"crossref","unstructured":"Strom N (2015) Scalable distributed dnn training using commodity gpu cloud computing. In: Sixteenth annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2015-354"},{"key":"1120_CR36","doi-asserted-by":"crossref","unstructured":"Dryden N, Moon T, Jacobs SA, Van\u00a0Essen B (2016) Communication quantization for data-parallel training of deep neural networks. In: 2016 2nd workshop on machine learning in HPC environments (MLHPC), pp 1\u20138, IEEE","DOI":"10.1109\/MLHPC.2016.004"},{"key":"1120_CR37","doi-asserted-by":"crossref","unstructured":"Aji AF, Heafield K (2017) Sparse communication for distributed gradient descent, Copenhagen, Denmark, pp 440\u2013445. In: Absolute values; convergence rates; gradient descent; machine translations; positively skewed; sparse matrices; speed up; stochastic gradient descent. http:\/\/dx.doi.org\/10.18653\/v1\/d17-1045","DOI":"10.18653\/v1\/D17-1045"},{"key":"1120_CR38","doi-asserted-by":"crossref","unstructured":"Chen C-Y, Choi J, Brand D, Agrawal A, Zhang W, Gopalakrishnan K (2018) Adacomp: adaptive residual gradient compression for data-parallel distributed training. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11728"},{"key":"1120_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3201203","volume":"71","author":"H Xing","year":"2022","unstructured":"Xing H, Xiao Z, Qu R, Zhu Z, Zhao B (2022) An efficient federated distillation learning system for multitask time series classification. IEEE Trans Instrum Meas 71:1\u201312. https:\/\/doi.org\/10.1109\/TIM.2022.3201203","journal-title":"IEEE Trans Instrum Meas"},{"key":"1120_CR40","first-page":"25","volume":"2022","author":"Z Zhuang","year":"2022","unstructured":"Zhuang Z, Tao H, Chen Y, Stojanovic V, Paszke W (2022) An optimal iterative learning control approach for linear systems with nonuniform trial lengths under input constraints. IEEE Trans Syst Man Cybern Syst 2022:25","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"18","key":"1120_CR41","doi-asserted-by":"publisher","first-page":"10139","DOI":"10.1002\/rnc.6354","volume":"32","author":"C Zhou","year":"2022","unstructured":"Zhou C, Tao H, Chen Y, Stojanovic V, Paszke W (2022) Robust point-to-point iterative learning control for constrained systems: a minimum energy approach. Int J Robust Nonlinear Control 32(18):10139\u201310161. https:\/\/doi.org\/10.1002\/rnc.6354","journal-title":"Int J Robust Nonlinear Control"},{"issue":"14","key":"1120_CR42","doi-asserted-by":"publisher","first-page":"3058","DOI":"10.1002\/rnc.3490","volume":"26","author":"V Stojanovic","year":"2016","unstructured":"Stojanovic V, Nedic N (2016) Joint state and parameter robust estimation of stochastic nonlinear systems. Int J Robust Nonlinear Control 26(14):3058\u20133074. https:\/\/doi.org\/10.1002\/rnc.3490","journal-title":"Int J Robust Nonlinear Control"},{"key":"1120_CR43","unstructured":"Bonawitz K, Eichner H, Grieskamp W, Huba D, Ingerman A, Ivanov V, Kiddon C, Kone\u010dn\u1ef3 J, Mazzocchi S, McMahan HB, et al (2019) Towards federated learning at scale: system design. arXiv:1902.01046"},{"key":"1120_CR44","unstructured":"Liu Z, Sun M, Zhou T, Huang G, Darrell T (2019) Rethinking the value of network pruning, New Orleans, LA, United states. In: Large models; learning rates; low-resource settings; network pruning; parameterized model; pruning algorithms; pruning methods; state of the art"},{"key":"1120_CR45","unstructured":"Wen W, Wu C, Wang Y, Chen Y, Li H (2016) Learning structured sparsity in deep neural networks, Barcelona, Spain, pp 2082\u20132090. In: Classification accuracy; compact structures; computation costs; computation resources; high demand; resource constrained devices; structured sparsities"},{"issue":"5","key":"1120_CR46","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1109\/LWC.2022.3149783","volume":"11","author":"D Wen","year":"2022","unstructured":"Wen D, Jeon K-J, Huang K (2022) Federated dropout a simple approach for enabling federated learning on resource constrained devices. IEEE Wirel Commun Lett 11(5):923\u2013927. https:\/\/doi.org\/10.1109\/LWC.2022.3149783","journal-title":"IEEE Wirel Commun Lett"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01120-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-023-01120-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01120-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T19:24:34Z","timestamp":1698434674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-023-01120-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,9]]},"references-count":46,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["1120"],"URL":"https:\/\/doi.org\/10.1007\/s40747-023-01120-5","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,9]]},"assertion":[{"value":"3 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}