{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T07:43:11Z","timestamp":1776325391631,"version":"3.50.1"},"reference-count":28,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T00:00:00Z","timestamp":1691971200000},"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":["2021YFA1000500(4)"],"award-info":[{"award-number":["2021YFA1000500(4)"]}]},{"name":"National Key Research and Development Program of China","award":["AoE\/E-601\/22-R"],"award-info":[{"award-number":["AoE\/E-601\/22-R"]}]},{"name":"Research Grants Council","award":["2021YFA1000500(4)"],"award-info":[{"award-number":["2021YFA1000500(4)"]}]},{"name":"Research Grants Council","award":["AoE\/E-601\/22-R"],"award-info":[{"award-number":["AoE\/E-601\/22-R"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>As a promising distributed learning paradigm, federated learning (FL) faces the challenge of communication\u2013computation bottlenecks in practical deployments. In this work, we mainly focus on the pruning, quantization, and coding of FL. By adopting a layer-wise operation, we propose an explicit and universal scheme: FedLP-Q (federated learning with layer-wise pruning-quantization). Pruning strategies for homogeneity\/heterogeneity scenarios, the stochastic quantization rule, and the corresponding coding scheme were developed. Both theoretical and experimental evaluations suggest that FedLP-Q improves the system efficiency of communication and computation with controllable performance degradation. The key novelty of FedLP-Q is that it serves as a joint pruning-quantization FL framework with layer-wise processing and can easily be applied in practical FL systems.<\/jats:p>","DOI":"10.3390\/e25081205","type":"journal-article","created":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T10:13:57Z","timestamp":1692008037000},"page":"1205","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Towards Efficient Federated Learning: Layer-Wise Pruning-Quantization Scheme and Coding Design"],"prefix":"10.3390","volume":"25","author":[{"given":"Zheqi","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"},{"name":"Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"},{"name":"Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8168-6870","authenticated-orcid":false,"given":"Gangtao","family":"Xin","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"},{"name":"Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenghui","family":"Peng","sequence":"additional","affiliation":[{"name":"Wireless Technology Laboratory, Huawei Technologies, Shanghai 200121, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0658-6079","authenticated-orcid":false,"given":"Pingyi","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"},{"name":"Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khaled B.","family":"Letaief","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,14]]},"reference":[{"key":"ref_1","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017, January 20\u201322). Communication-efficient learning of deep networks from decentralized data. Proceedings of the Artificial Intelligence and Statistics, PMLR, Fort Lauderdale, FL, USA."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/MCOM.2019.1900271","article-title":"The roadmap to 6G: AI empowered wireless networks","volume":"57","author":"Letaief","year":"2019","journal-title":"IEEE Commun. Mag."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1109\/JSAC.2021.3126076","article-title":"Edge artificial intelligence for 6G: Vision, enabling technologies, and applications","volume":"40","author":"Letaief","year":"2021","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.eng.2021.12.002","article-title":"Federated learning for 6G: Applications, challenges, and opportunities","volume":"8","author":"Yang","year":"2022","journal-title":"Engineering"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"9482","DOI":"10.1109\/JIOT.2023.3234196","article-title":"How global observation works in Federated Learning: Integrating vertical training into Horizontal Federated Learning","volume":"10","author":"Wan","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1109\/JIOT.2021.3078514","article-title":"Federated multiagent actor\u2013critic learning for age sensitive mobile-edge computing","volume":"9","author":"Zhu","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3339474","article-title":"Federated machine learning: Concept and applications","volume":"10","author":"Yang","year":"2019","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"key":"ref_8","unstructured":"Zhu, Z., Fan, P., Peng, C., and Letaief, K.B. (2022). ISFL: Federated Learning for Non-i.i.d. Data with Local Importance Sampling. arXiv."},{"key":"ref_9","unstructured":"Chen, M., Mao, B., and Ma, T. (2019, January 6\u20139). Efficient and robust asynchronous federated learning with stragglers. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_10","first-page":"50","article-title":"Federated learning: Challenges, methods, and future directions","volume":"37","author":"Li","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000083","article-title":"Advances and open problems in federated learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_12","unstructured":"Han, S., Mao, H., and Dally, W.J. (2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv."},{"key":"ref_13","unstructured":"Caldas, S., Kone\u010dny, J., McMahan, H.B., and Talwalkar, A. (2018). Expanding the reach of federated learning by reducing client resource requirements. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1572","DOI":"10.1109\/LWC.2021.3074605","article-title":"Adaptive network pruning for wireless federated learning","volume":"10","author":"Liu","year":"2021","journal-title":"IEEE Wirel. Commun. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1109\/LWC.2022.3149783","article-title":"Federated Dropout\u2014A Simple Approach for Enabling Federated Learning on Resource Constrained Devices","volume":"11","author":"Wen","year":"2022","journal-title":"IEEE Wirel. Commun. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Cheng, G., Charles, Z., Garrett, Z., and Rush, K. (2022, January 18\u201324). Does Federated Dropout Actually Work?. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPRW56347.2022.00382"},{"key":"ref_17","first-page":"12876","article-title":"Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout","volume":"34","author":"Horvath","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chen, Y., Chen, Z., Wu, P., and Yu, H. (2022). FedOBD: Opportunistic Block Dropout for Efficiently Training Large-scale Neural Networks through Federated Learning. arXiv.","DOI":"10.24963\/ijcai.2023\/394"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Shi, Y., Luo, J., Wang, F., Peng, C., Fan, P., and Letaief, K.B. (2023). FedLP: Layer-wise Pruning Mechanism for Communication-Computation Efficient Federated Learning. arXiv.","DOI":"10.1109\/ICC45041.2023.10278563"},{"key":"ref_20","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume":"30","author":"Alistarh","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_21","unstructured":"H\u00f6nig, R., Zhao, Y., and Mullins, R. (2022, January 17\u201323). DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning. Proceedings of the International Conference on Machine Learning, PMLR, Baltimore, MD, USA."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1109\/TWC.2022.3190512","article-title":"Hierarchical federated learning with quantization: Convergence analysis and system design","volume":"22","author":"Liu","year":"2022","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_23","unstructured":"Amiri, M.M., Gunduz, D., Kulkarni, S.R., and Poor, H.V. (2020). Federated learning with quantized global model updates. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TSP.2020.3046971","article-title":"UVeQFed: Universal vector quantization for federated learning","volume":"69","author":"Shlezinger","year":"2020","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_25","unstructured":"Reisizadeh, A., Mokhtari, A., Hassani, H., Jadbabaie, A., and Pedarsani, R. (2020, January 26\u201328). Fedpaq: A communication-efficient federated learning method with periodic averaging and quantization. Proceedings of the International Conference on Artificial Intelligence and Statistics, PMLR, Online."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1109\/JSTSP.2022.3142678","article-title":"Communication-efficient federated learning via predictive coding","volume":"16","author":"Yue","year":"2022","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"13638","DOI":"10.1109\/JIOT.2022.3145865","article-title":"IoT Device Friendly and Communication-Efficient Federated Learning via Joint Model Pruning and Quantization","volume":"9","author":"Prakash","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1109\/TIT.1975.1055349","article-title":"Universal codeword sets and representations of the integers","volume":"21","author":"Elias","year":"1975","journal-title":"IEEE Trans. Inf. Theory"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/8\/1205\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:32:58Z","timestamp":1760128378000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/8\/1205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,14]]},"references-count":28,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["e25081205"],"URL":"https:\/\/doi.org\/10.3390\/e25081205","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,14]]}}}