{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T11:40:19Z","timestamp":1761738019473,"version":"build-2065373602"},"reference-count":40,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62302540"],"award-info":[{"award-number":["No. 62302540"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Foundation of the Henan Key Laboratory of Cyberspace Situation Awareness","award":["No. HNTS2022020"],"award-info":[{"award-number":["No. HNTS2022020"]}]},{"name":"Key Research and Development Program of Henan Province","award":["No. 251111212000"],"award-info":[{"award-number":["No. 251111212000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Federated learning (FL), as a privacy-preserving distributed machine learning paradigm, demonstrates unique advantages in addressing data silo problems. However, the prevalent statistical heterogeneity (data distribution disparities) and system heterogeneity (device capability variations) in practical applications significantly hinder FL performance. Traditional synchronous FL suffers from severe waiting delays due to its mandatory synchronization mechanism, while asynchronous approaches incur model bias issues caused by training pace discrepancies. To tackle these challenges, this paper proposes the SACW framework, which effectively balances training efficiency and model quality through a semi-asynchronous training mechanism. The framework adopts a hybrid strategy of \u201casynchronous client training\u2013synchronous server aggregation,\u201d combined with an adaptive weighting algorithm based on model staleness and data volume. This approach significantly improves system resource utilization and mitigates system heterogeneity. Simultaneously, the server employs data distribution-aware client clustering and hierarchical selection strategies to construct a training environment characterized by \u201cinter-cluster heterogeneity and intra-cluster homogeneity.\u201d Representative clients from each cluster are selected to participate in model aggregation, thereby addressing data heterogeneity. We conduct comprehensive comparisons with mainstream synchronous and asynchronous FL methods and perform extensive experiments across various model architectures and datasets. The results demonstrate that SACW achieves better performance in both training efficiency and model accuracy under scenarios with system and data heterogeneity.<\/jats:p>","DOI":"10.3390\/computers14110464","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T04:26:29Z","timestamp":1761711989000},"page":"464","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SACW: Semi-Asynchronous Federated Learning with Client Selection and Adaptive Weighting"],"prefix":"10.3390","volume":"14","author":[{"given":"Shuaifeng","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer, Zhongyuan University of Technology, Zhengzhou 450007, China"}]},{"given":"Fangfang","family":"Shan","sequence":"additional","affiliation":[{"name":"College of Computer, Zhongyuan University of Technology, Zhengzhou 450007, China"},{"name":"Henan Key Laboratory of Cyberspace Situation Awareness, Zhengzhou 450001, China"}]},{"given":"Shiqi","family":"Mao","sequence":"additional","affiliation":[{"name":"College of Computer, Zhongyuan University of Technology, Zhengzhou 450007, China"}]},{"given":"Yanlong","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Computer, Zhongyuan University of Technology, Zhengzhou 450007, China"}]},{"given":"Fengjun","family":"Miao","sequence":"additional","affiliation":[{"name":"College of Computer, Zhongyuan University of Technology, Zhengzhou 450007, China"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer, Zhongyuan University of Technology, Zhengzhou 450007, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/MNET.2019.1800286","article-title":"In-edge AI: Intelligentizing mobile edge computing, caching and communication by federated learning","volume":"33","author":"Wang","year":"2019","journal-title":"IEEE Netw."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_3","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\u00ae Mach. Learn."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/IOTM.004.2100182","article-title":"Federated learning for the internet of things: Applications, challenges, and opportunities","volume":"5","author":"Zhang","year":"2022","journal-title":"IEEE Internet Things Mag."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"106854","DOI":"10.1016\/j.cie.2020.106854","article-title":"A review of applications in federated learning","volume":"149","author":"Li","year":"2020","journal-title":"Comput. Ind. Eng."},{"key":"ref_6","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_7","doi-asserted-by":"crossref","first-page":"21811","DOI":"10.1109\/JIOT.2023.3299573","article-title":"Client selection in federated learning: Principles, challenges, and opportunities","volume":"10","author":"Fu","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1129","DOI":"10.1007\/s11831-023-10011-4","article-title":"A review of client selection methods in federated learning","volume":"31","author":"Mayhoub","year":"2024","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_9","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017). Communication-efficient learning of deep networks from decentralized data. Artificial Intelligence and Statistics, PMLR."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/JIOT.2021.3095077","article-title":"A survey on federated learning for resource-constrained IoT devices","volume":"9","author":"Imteaj","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sasindran, Z., Yelchuri, H., and Prabhakar, T.V. (2023, January 18\u201323). Ed-Fed: A generic federated learning framework with resource-aware client selection for edge devices. Proceedings of the 2023 International Joint Conference on Neural Networks (IJCNN), Gold Coast, Australia.","DOI":"10.1109\/IJCNN54540.2023.10191316"},{"key":"ref_12","unstructured":"Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., and Chandra, V. (2018). Federated learning with non-IID data. arXiv."},{"key":"ref_13","first-page":"11498","article-title":"FedGCR: Achieving Performance and Fairness for Federated Learning with Distinct Client Types via Group Customization and Reweighting","volume":"38","author":"Cheng","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_14","unstructured":"Moe, C., Koyejo, S., and Gupta, I. (2019). Asynchronous federated optimization. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"108429","DOI":"10.1016\/j.comnet.2021.108429","article-title":"Communication-efficient asynchronous federated learning in resource-constrained edge computing","volume":"199","author":"Liu","year":"2021","journal-title":"Comput. Netw."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"100595","DOI":"10.1016\/j.cosrev.2023.100595","article-title":"Asynchronous federated learning on heterogeneous devices: A survey","volume":"50","author":"Xu","year":"2023","journal-title":"Comput. Sci. Rev."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1996","DOI":"10.1109\/TPDS.2021.3134647","article-title":"AUCTION: Automated and quality-aware client selection framework for efficient federated learning","volume":"33","author":"Deng","year":"2021","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1145\/3625558","article-title":"Heterogeneous Federated Learning: State-of-the-art and Research Challenges","volume":"56","author":"Ye","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, Q., He, B., and Song, D. (2021, January 20\u201325). Model-contrastive federated learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, X.C., and Zhan, D.C. (2021, January 14\u201318). FedRS: Federated learning with restricted softmax for label distribution non-IID data. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery Data Mining, Singapore.","DOI":"10.1145\/3447548.3467254"},{"key":"ref_21","unstructured":"Zhang, J., Li, Z., Li, B., Xu, J., Wu, S., Ding, S., and Wu, C. (2022, January 17\u201323). Federated learning with label distribution skew via logits calibration. Proceedings of the International Conference on Machine Learning, Baltimore, MD, USA."},{"key":"ref_22","unstructured":"Nguyen, J., Malik, K., Zhan, H., Yousefpour, A., Rabbat, M., Malek, M., and Huba, D. (2022, January 28\u201330). Federated learning with buffered asynchronous aggregation. Proceedings of the International Conference on Artificial Intelligence and Statistics, Virtual."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1109\/TPAMI.2023.3332428","article-title":"Multi-Stage Asynchronous Federated Learning With Adaptive Differential Privacy","volume":"46","author":"Li","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3654","DOI":"10.1109\/JSAC.2021.3118435","article-title":"FedSA: A semi-asynchronous federated learning mechanism in heterogeneous edge computing","volume":"39","author":"Ma","year":"2021","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1109\/TC.2020.2994391","article-title":"SAFA: A semi-asynchronous protocol for fast federated learning with low overhead","volume":"70","author":"Wu","year":"2020","journal-title":"IEEE Trans. Comput."},{"key":"ref_26","unstructured":"Zakerinia, H., Talaei, S., Nadiradze, G., and Alistarh, D. (2024, January 2\u20134). Communication-efficient federated learning with data and client heterogeneity. Proceedings of the International Conference on Artificial Intelligence and Statistics, Valencia, Spain."},{"key":"ref_27","unstructured":"Kone\u010dn\u00fd, J., McMahan, B., and Ramage, D. (2015). Federated optimization: Distributed optimization beyond the datacenter. arXiv."},{"key":"ref_28","unstructured":"Ester, M., and Sander, J. (1996, January 2\u20134). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the KDD\u201996: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, Portland, OR, USA."},{"key":"ref_29","unstructured":"Davies, P., Gurunathan, V., Moshrefi, N., Ashkboos, S., and Alistarh, D. (2020). New bounds for distributed mean estimation and variance reduction. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"2002","journal-title":"Proc. IEEE"},{"key":"ref_31","unstructured":"Xiao, H., Rasul, K., and Vollgraf, R. (2017). Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv."},{"key":"ref_32","unstructured":"Krizhevsky, A. (2025, October 20). Dataset: Learning Multiple Layers of Features from Tiny Images. Available online: https:\/\/service.tib.eu\/ldmservice\/dataset\/learning-multiple-layers-of-features-from-tiny-images."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Guo, S., Yang, X., Feng, J., Ding, Y., Wang, W., Feng, Y., and Liao, Q. (2023). FedGR: Federated learning with gravitation regulation for double imbalance distribution. International Conference on Database Systems for Advanced Applications, Springer Nature Switzerland.","DOI":"10.1007\/978-3-031-30637-2_47"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"9587","DOI":"10.1109\/TNNLS.2022.3160699","article-title":"Towards personalized federated learning","volume":"34","author":"Tan","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"He, Y., Tan, H., Luo, W., Mao, H., Ma, D., Feng, S., and Fan, J. (2011, January 7\u20139). MR-DBSCAN: An Efficient Parallel Density-Based Clustering Algorithm Using MapReduce. Proceedings of the 2011 IEEE 17th International Conference on Parallel and Distributed Systems, Tainan, Taiwan.","DOI":"10.1109\/ICPADS.2011.83"},{"key":"ref_36","unstructured":"Zhu, L., Liu, Z., and Han, S. (2019, January 8\u201314). Deep leakage from gradients. Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_37","unstructured":"Dwork, C. (2006, January 10\u201314). Differential privacy. Proceedings of the 33rd international conference on Automata, Languages and Programming\u2014Volume Part II (ICALP\u201906), Venice, Italy."},{"key":"ref_38","first-page":"103992","article-title":"Efficient adaptive defense scheme for differential privacy in federated learning","volume":"89","author":"Shan","year":"2025","journal-title":"J. Inf. Secur. Appl."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"Johnson","year":"2019","journal-title":"J. Big Data"},{"key":"ref_40","unstructured":"Diao, Y., Li, Q., and He, B. (March, January 25). Exploiting Label Skews in Federated Learning with Model Concatenation. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/11\/464\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T04:54:16Z","timestamp":1761713656000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/11\/464"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":40,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["computers14110464"],"URL":"https:\/\/doi.org\/10.3390\/computers14110464","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,27]]}}}