{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:39:12Z","timestamp":1773002352618,"version":"3.50.1"},"reference-count":45,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T00:00:00Z","timestamp":1742860800000},"content-version":"vor","delay-in-days":83,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1802200"],"award-info":[{"award-number":["2018YFB1802200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFB1804403"],"award-info":[{"award-number":["2019YFB1804403"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019024","name":"Guangdong Polytechnic Normal University","doi-asserted-by":"publisher","award":["2022SDKYA029"],"award-info":[{"award-number":["2022SDKYA029"]}],"id":[{"id":"10.13039\/100019024","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019024","name":"Guangdong Polytechnic Normal University","doi-asserted-by":"publisher","award":["22GPNUZDJS26"],"award-info":[{"award-number":["22GPNUZDJS26"]}],"id":[{"id":"10.13039\/100019024","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972104"],"award-info":[{"award-number":["61972104"]}],"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":["61902080"],"award-info":[{"award-number":["61902080"]}],"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":["62002072"],"award-info":[{"award-number":["62002072"]}],"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":["61702120"],"award-info":[{"award-number":["61702120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004000","name":"Guangzhou Science and Technology Program key projects","doi-asserted-by":"publisher","award":["201803010081"],"award-info":[{"award-number":["201803010081"]}],"id":[{"id":"10.13039\/501100004000","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004000","name":"Guangzhou Science and Technology Program key projects","doi-asserted-by":"publisher","award":["202002020035"],"award-info":[{"award-number":["202002020035"]}],"id":[{"id":"10.13039\/501100004000","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011478","name":"Foshan Science and Technology Bureau","doi-asserted-by":"publisher","award":["2018IT100283"],"award-info":[{"award-number":["2018IT100283"]}],"id":[{"id":"10.13039\/501100011478","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>In image analysis scenarios such as the Internet of Things and the metaverse, the introduction of federated learning (FL) is an effective solution to safeguard user data security and meet low\u2010latency requirements during the machine learning process. However, due to the constrained computational power and memory of devices, facilitating the local training of complex models becomes challenging, thereby posing a significant obstacle to the application of FL. Consequently, a lightweight dynamic hierarchical neural network model and its learning paradigm are proposed in this study. Specifically, a lightweight compression method is designed based on enlarged receptive fields and separable convolutions to reduce redundancy in convolutional layer feature maps. A dynamic model partitioning method is devised, grounded in the Q\u2010Learning reinforcement learning algorithm, to enable collaborative model training across multiple devices and enhance the utilization efficiency of device computing and storage resources. Furthermore, a hierarchical federated partition learning (HFSL) paradigm based on complete weight sharing is introduced to facilitate the compatibility of partitioned models with FL. Experimental results show that our lightweight model outperforms existing models in terms of accuracy, lightweight degree, and efficiency on image analysis tasks. Moreover, the proposed HFSL paradigm achieves performance comparable to centralized training.<\/jats:p>","DOI":"10.1155\/int\/6833629","type":"journal-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T08:26:14Z","timestamp":1743063974000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Lightweight Dynamic Hierarchical Neural Network Model and Learning Paradigm"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0282-3817","authenticated-orcid":false,"given":"Liping","family":"Liao","sequence":"first","affiliation":[]},{"given":"Junlong","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Wenjing","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3293-6658","authenticated-orcid":false,"given":"Jun","family":"Cai","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,3,25]]},"reference":[{"key":"e_1_2_11_1_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583683"},{"key":"e_1_2_11_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2023.3306931"},{"key":"e_1_2_11_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ojcoms.2023.3320646"},{"key":"e_1_2_11_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/tsc.2024.3376194"},{"key":"e_1_2_11_5_2","unstructured":"SimonyanK.andZissermanA. Very Deep Convolutional Networks for Large-Scale Image Recognition 2014 https:\/\/arxiv.org\/abs\/1409.1556."},{"key":"e_1_2_11_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3280899"},{"key":"e_1_2_11_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2022.3224969"},{"key":"e_1_2_11_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3066410"},{"key":"e_1_2_11_9_2","doi-asserted-by":"crossref","unstructured":"DuM. MaZ. andLiuY. Model Compression Method Based on Knowledge Distilling and Adversarial Learning Proceedings of the Complex System Design and Management 2023 Springer 118\u2013129.","DOI":"10.1007\/978-981-99-6511-3_11"},{"key":"e_1_2_11_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3050628"},{"key":"e_1_2_11_11_2","doi-asserted-by":"crossref","unstructured":"ZhangX. ZhouX. LinM. andSunJ. Shufflenet: An Extremely Efficient Convolutional Neural Network for Mobile Devices Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018 6848\u20136856.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"e_1_2_11_12_2","unstructured":"HowardA. G. ZhuM. ChenB.et al. Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications 2017 https:\/\/arxiv.org\/abs\/1704.04861."},{"key":"e_1_2_11_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2022.3197809"},{"key":"e_1_2_11_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2022.3206817"},{"key":"e_1_2_11_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/mcom.001.2000373"},{"key":"e_1_2_11_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/jsac.2021.3118403"},{"key":"e_1_2_11_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2022.3176469"},{"key":"e_1_2_11_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2022.3165824"},{"key":"e_1_2_11_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2022.3177569"},{"key":"e_1_2_11_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.05.003"},{"key":"e_1_2_11_21_2","doi-asserted-by":"crossref","unstructured":"JeonJ.andKimJ. Privacy-Sensitive Parallel Split Learning Proceedings of the 2020 International Conference on Information Networking (ICOIN) 2020 IEEE 7\u20139.","DOI":"10.1109\/ICOIN48656.2020.9016486"},{"key":"e_1_2_11_22_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"e_1_2_11_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2023.3280405"},{"key":"e_1_2_11_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/tsc.2023.3342435"},{"key":"e_1_2_11_25_2","first-page":"9969","article-title":"Ghostnetv2: Enhance Cheap Operation With Long-Range Attention","volume":"35","author":"Tang Y.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_26_2","unstructured":"QinZ. YuF. LiuC. andChenX. How Convolutional Neural Network See the World-A Survey of Convolutional Neural Network Visualization Methods 2018 https:\/\/arxiv.org\/abs\/1804.11191."},{"key":"e_1_2_11_27_2","unstructured":"LEA China Mobile Communications Group Terminal Co White Paper on End-Side Computing Network 2022 3\u20136."},{"key":"e_1_2_11_28_2","unstructured":"TanM.andLeQ. Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks Proceedings of the International Conference on Machine Learning 2019 PMLR 6105\u20136114."},{"key":"e_1_2_11_29_2","doi-asserted-by":"crossref","unstructured":"SzegedyC. LiuW. JiaY.et al. Going Deeper With Convolutions Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015 1\u20139 https:\/\/doi.org\/10.1109\/cvpr.2015.7298594 2-s2.0-84937522268.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_11_30_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep Residual Learning for Image Recognition Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_11_31_2","doi-asserted-by":"crossref","unstructured":"WuB. WanA. YueX.et al. Shift: A Zero Flop Zero Parameter Alternative to Spatial Convolutions Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018 9127\u20139135.","DOI":"10.1109\/CVPR.2018.00951"},{"key":"e_1_2_11_32_2","unstructured":"MolchanovP. MallyaA. TyreeS. FrosioI. andKautzJ. Importance Estimation for Neural Network Pruning Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2019 11 264\u2013311 272."},{"key":"e_1_2_11_33_2","unstructured":"EvciU. GaleT. MenickJ. CastroP. S. andElsenE. Rigging the Lottery: Making All Tickets Winners Proceedings of the International Conference on Machine Learning 2020 PMLR 2943\u20132952."},{"key":"e_1_2_11_34_2","doi-asserted-by":"crossref","unstructured":"LinM. JiR. WangY.et al. Hrank: Filter Pruning Using High-Rank Feature Map Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2020 1529\u20131538.","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"e_1_2_11_35_2","doi-asserted-by":"crossref","unstructured":"YuanL. ChenY. WangT.et al. Tokens-to-Token Vit: Training Vision Transformers From Scratch on Imagenet Proceedings of the IEEE\/CVF International Conference on Computer Vision 2021 558\u2013567.","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"e_1_2_11_36_2","unstructured":"TouvronH. CordM. DouzeM. MassaF. SablayrollesA. andJ\u00b4egouH. Training Data-Efficient Image Transformers & Distillation Through Attention Proceedings of the International Conference on Machine Learning 2021 PMLR 10 347\u2013410 357."},{"key":"e_1_2_11_37_2","unstructured":"MehtaS.andRastegariM. Separable Self-Attention for Mobile Vision Transformers 2022 https:\/\/arxiv.org\/abs\/2206.02680."},{"key":"e_1_2_11_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"e_1_2_11_39_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20222"},{"key":"e_1_2_11_40_2","doi-asserted-by":"crossref","unstructured":"YuL.andXiangW. X-Pruner: Explainable Pruning for Vision Transformers Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2023 24 355\u2013424 363 https:\/\/doi.org\/10.1109\/cvpr52729.2023.02333.","DOI":"10.1109\/CVPR52729.2023.02333"},{"key":"e_1_2_11_41_2","doi-asserted-by":"crossref","unstructured":"HanD. PanX. HanY. SongS. andHuangG. Flatten Transformer: Vision Transformer Using Focused Linear Attention Proceedings of the IEEE\/CVF International Conference on Computer Vision 2023 5961\u20135971.","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"e_1_2_11_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127189"},{"key":"e_1_2_11_43_2","unstructured":"LiuJ. TangD. HuangY.et al. Updp: A Unified Progressive Depth Pruner for Cnn and Vision Transformer 2024 https:\/\/arxiv.org\/abs\/2401.06426."},{"key":"e_1_2_11_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/tccn.2019.2919300"},{"key":"e_1_2_11_45_2","doi-asserted-by":"crossref","unstructured":"LeeK.andYuN. Y. End-to-End Learning-Based Wireless Image Recognition Using the Pyramidnet in Edge Intelligence Proceedings of the 2023 IEEE 34th Annual International Symposium on Personal Indoor and Mobile Radio Communications (PIMRC) 2023 IEEE 1\u20136.","DOI":"10.1109\/PIMRC56721.2023.10293934"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/6833629","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/6833629","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/6833629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:13:26Z","timestamp":1772993606000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/6833629"}},"subtitle":[],"editor":[{"given":"Riccardo","family":"Ortale","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/6833629"],"URL":"https:\/\/doi.org\/10.1155\/int\/6833629","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-07-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"6833629"}}