{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:21:06Z","timestamp":1783610466112,"version":"3.55.0"},"reference-count":45,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T00:00:00Z","timestamp":1687996800000},"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 (NSFC)","doi-asserted-by":"publisher","award":["61976243"],"award-info":[{"award-number":["61976243"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["61971458"],"award-info":[{"award-number":["61971458"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["224200510004"],"award-info":[{"award-number":["224200510004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["231100220600"],"award-info":[{"award-number":["231100220600"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["22HASTIT014"],"award-info":[{"award-number":["22HASTIT014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["23ZX003"],"award-info":[{"award-number":["23ZX003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Leading talents of science and technology in the Central Plain of China","award":["61976243"],"award-info":[{"award-number":["61976243"]}]},{"name":"Leading talents of science and technology in the Central Plain of China","award":["61971458"],"award-info":[{"award-number":["61971458"]}]},{"name":"Leading talents of science and technology in the Central Plain of China","award":["224200510004"],"award-info":[{"award-number":["224200510004"]}]},{"name":"Leading talents of science and technology in the Central Plain of China","award":["231100220600"],"award-info":[{"award-number":["231100220600"]}]},{"name":"Leading talents of science and technology in the Central Plain of China","award":["22HASTIT014"],"award-info":[{"award-number":["22HASTIT014"]}]},{"name":"Leading talents of science and technology in the Central Plain of China","award":["23ZX003"],"award-info":[{"award-number":["23ZX003"]}]},{"name":"Longmen Laboratory Major Project","award":["61976243"],"award-info":[{"award-number":["61976243"]}]},{"name":"Longmen Laboratory Major Project","award":["61971458"],"award-info":[{"award-number":["61971458"]}]},{"name":"Longmen Laboratory Major Project","award":["224200510004"],"award-info":[{"award-number":["224200510004"]}]},{"name":"Longmen Laboratory Major Project","award":["231100220600"],"award-info":[{"award-number":["231100220600"]}]},{"name":"Longmen Laboratory Major Project","award":["22HASTIT014"],"award-info":[{"award-number":["22HASTIT014"]}]},{"name":"Longmen Laboratory Major Project","award":["23ZX003"],"award-info":[{"award-number":["23ZX003"]}]},{"name":"Science &amp; Technology Innovation Talents in the University of Henan Province of China","award":["61976243"],"award-info":[{"award-number":["61976243"]}]},{"name":"Science &amp; Technology Innovation Talents in the University of Henan Province of China","award":["61971458"],"award-info":[{"award-number":["61971458"]}]},{"name":"Science &amp; Technology Innovation Talents in the University of Henan Province of China","award":["224200510004"],"award-info":[{"award-number":["224200510004"]}]},{"name":"Science &amp; Technology Innovation Talents in the University of Henan Province of China","award":["231100220600"],"award-info":[{"award-number":["231100220600"]}]},{"name":"Science &amp; Technology Innovation Talents in the University of Henan Province of China","award":["22HASTIT014"],"award-info":[{"award-number":["22HASTIT014"]}]},{"name":"Science &amp; Technology Innovation Talents in the University of Henan Province of China","award":["23ZX003"],"award-info":[{"award-number":["23ZX003"]}]},{"name":"University of Henan Province, China","award":["61976243"],"award-info":[{"award-number":["61976243"]}]},{"name":"University of Henan Province, China","award":["61971458"],"award-info":[{"award-number":["61971458"]}]},{"name":"University of Henan Province, China","award":["224200510004"],"award-info":[{"award-number":["224200510004"]}]},{"name":"University of Henan Province, China","award":["231100220600"],"award-info":[{"award-number":["231100220600"]}]},{"name":"University of Henan Province, China","award":["22HASTIT014"],"award-info":[{"award-number":["22HASTIT014"]}]},{"name":"University of Henan Province, China","award":["23ZX003"],"award-info":[{"award-number":["23ZX003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Federated learning is served as a novel distributed training framework that enables multiple clients of the internet of things to collaboratively train a global model while the data remains local. However, the implement of federated learning faces many problems in practice, such as the large number of training for convergence due to the size of model and the lack of adaptivity by the stochastic gradient-based update at the client side. Meanwhile, it is sensitive to noise during the optimization process that can affect the performance of the final model. For these reasons, we propose Federated Adaptive learning based on Derivative Term, called FedADT in this paper, which incorporates adaptive step size and difference of gradient in the update of local model. To further reduce the influence of noise on the derivative term that is estimated by difference of gradient, we use moving average decay on the derivative term. Moreover, we analyze the convergence performance of the proposed algorithm for non-convex objective function, i.e., the convergence rate of 1\/nT can be achieved by choosing appropriate hyper-parameters, where n is the number of clients and T is the number of iterations, respectively. Finally, various experiments for the image classification task are conducted by training widely used convolutional neural network on MNIST and Fashion MNIST datasets to verify the effectiveness of FedADT. In addition, the receiver operating characteristic curve is used to display the result of the proposed algorithm by predicting the categories of clothing on the Fashion MNIST dataset.<\/jats:p>","DOI":"10.3390\/s23136034","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T01:14:12Z","timestamp":1688087652000},"page":"6034","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["FedADT: An Adaptive Method Based on Derivative Term for Federated Learning"],"prefix":"10.3390","volume":"23","author":[{"given":"Huimin","family":"Gao","sequence":"first","affiliation":[{"name":"School of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1572-5293","authenticated-orcid":false,"given":"Qingtao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China"},{"name":"Intelligent System Science and Technology Innovation Center, Longmen Laboratory, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhui","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junlong","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2523-1089","authenticated-orcid":false,"given":"Mingchuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,29]]},"reference":[{"key":"ref_1","unstructured":"Kone\u010dn\u00fd, J., McMahan, H.B., Yu, F.X., Richt\u00e1rik, P., Suresh, A.T., and Bacon, D. (2016). Federated Learning: Strategies for Improving Communication Efficiency. arXiv."},{"key":"ref_2","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 20th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Yang, Y., Hong, Y., and Park, J. (2021). Efficient Gradient Updating Strategies with Adaptive Power Allocation for Federated Learning over Wireless Backhaul. Sensors, 21.","DOI":"10.3390\/s21206791"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yang, W., Zhang, Y., Ye, K., Li, L., and Xu, C. (2019, January 25\u201330). FFD: A Federated Learning Based Method for Credit Card Fraud Detection. Proceedings of the Big Data\u2014BigData 2019\u20148th International Congress, San Diego, CA, USA. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-030-23551-2_2"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s41666-020-00082-4","article-title":"Federated Learning for Healthcare Informatics","volume":"5","author":"Xu","year":"2021","journal-title":"J. Healthc. Inform. Res."},{"key":"ref_6","unstructured":"Stich, S.U. (2019, January 6\u20139). Local SGD Converges Fast and Communicates Little. Proceedings of the 7th International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_7","unstructured":"Wang, J., and Joshi, G. (2018). Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms. arXiv."},{"key":"ref_8","unstructured":"Khaled, A., Mishchenko, K., and Richt\u00e1rik, P. (2020, January 26\u201328). Tighter Theory for Local SGD on Identical and Heterogeneous Data. Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, Palermo, Italy."},{"key":"ref_9","unstructured":"Yu, H., Jin, R., and Yang, S. (2019, January 10\u201315). On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_10","unstructured":"Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., and Smith, V. (2020, January 2\u20134). Federated Optimization in Heterogeneous Networks. Proceedings of the Proceedings of Machine Learning and Systems, Austin, TX, USA."},{"key":"ref_11","unstructured":"Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S.J., Stich, S.U., and Suresh, A.T. (2020, January 13\u201318). SCAFFOLD: Stochastic Controlled Averaging for Federated Learning. Proceedings of the 37th International Conference on Machine Learning, Virtual."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1754","DOI":"10.1109\/TPDS.2020.2975189","article-title":"Accelerating Federated Learning via Momentum Gradient Descent","volume":"31","author":"Liu","year":"2020","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ozfatura, E., Ozfatura, K., and G\u00fcnd\u00fcz, D. (2021, January 12\u201320). FedADC: Accelerated Federated Learning with Drift Control. Proceedings of the IEEE International Symposium on Information Theory, Virtual Event.","DOI":"10.1109\/ISIT45174.2021.9517850"},{"key":"ref_14","unstructured":"Reddi, S.J., Charles, Z., Zaheer, M., Garrett, Z., Rush, K., Kone\u010dn\u00fd, J., Kumar, S., and McMahan, H.B. (2021, January 3\u20137). Adaptive Federated Optimization. Proceedings of the 9th International Conference on Learning Representations, Virtual Event."},{"key":"ref_15","unstructured":"Khanduri, P., Sharma, P., Yang, H., Hong, M., Liu, J., Rajawat, K., and Varshney, P.K. (2021, January 6\u201314). STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning. Proceedings of the Advances in Neural Information Processing Systems, online."},{"key":"ref_16","unstructured":"Xu, A., and Huang, H. (2021). Double Momentum SGD for Federated Learning. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Chen, X., Li, X., and Li, P. (2020, January 19\u201320). Toward Communication Efficient Adaptive Gradient Method. Proceedings of the FODS\u201920: ACM-IMS Foundations of Data Science Conference, Virtual Event.","DOI":"10.1145\/3412815.3416891"},{"key":"ref_18","unstructured":"Wang, Y., Lin, L., and Chen, J. (2022, January 17\u201323). Communication-Efficient Adaptive Federated Learning. Proceedings of the International Conference on Machine Learning, Baltimore, MD, USA."},{"key":"ref_19","unstructured":"Ogata, K. (2010). Modern Control Engineering, Prentice Hall."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3010","DOI":"10.1109\/TNNLS.2020.3048031","article-title":"PID Controller-Guided Attention Neural Network Learning for Fast and Effective Real Photographs Denoising","volume":"33","author":"Ma","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"An, W., Wang, H., Sun, Q., Xu, J., Dai, Q., and Zhang, L. (2018, January 18\u201323). A PID Controller Approach for Stochastic Optimization of Deep Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00889"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Wang, W., Cheng, J., and Lu, H. (2020, January 6\u201310). Rethinking The Pid Optimizer For Stochastic Optimization Of Deep Networks. Proceedings of the IEEE International Conference on Multimedia and Expo, London, UK.","DOI":"10.1109\/ICME46284.2020.9102970"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1146\/annurev-control-053018-023825","article-title":"A tour of reinforcement learning: The view from continuous control","volume":"2","author":"Recht","year":"2019","journal-title":"Annu. Rev. Control Robot. Auton. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","article-title":"Some methods of speeding up the convergence of iteration methods","volume":"4","author":"Polyak","year":"1964","journal-title":"USSR Comput. Math. Math. Phys."},{"key":"ref_25","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate O (1\/k2)","volume":"27","author":"Nesterov","year":"1983","journal-title":"Sov. Math. Dokl."},{"key":"ref_26","unstructured":"Goodfellow, I.J., Bengio, Y., and Courville, A.C. (2016). Deep Learning, MIT Press."},{"key":"ref_27","unstructured":"Sutskever, I., Martens, J., Dahl, G.E., and Hinton, G.E. (2013, January 16\u201321). On the importance of initialization and momentum in deep learning. Proceedings of the 30th International Conference on Machine Learning, Atlanta, GA, USA."},{"key":"ref_28","unstructured":"Liu, D., and Lu, Z. (2021). The Convergence Rate of SGD\u2019s Final Iterate: Analysis on Dimension Dependence. arXiv."},{"key":"ref_29","unstructured":"Amir, I., Koren, T., and Livni, R. (2021, January 15\u201319). SGD Generalizes Better Than GD (And Regularization Doesn\u2019t Help). Proceedings of the Conference on Learning Theory, Boulder, CO, USA."},{"key":"ref_30","first-page":"2121","article-title":"Adaptive Subgradient Methods for Online Learning and Stochastic Optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_31","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_32","unstructured":"Reddi, S.J., Kale, S., and Kumar, S. (May, January 30). On the Convergence of Adam and Beyond. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_33","unstructured":"Zaheer, M., Reddi, S.J., Sachan, D.S., Kale, S., and Kumar, S. (2018, January 3\u20138). Adaptive Methods for Nonconvex Optimization. Proceedings of the Advances in Neural Information Processing Systems, Montr\u00e9al, QC, Canada."},{"key":"ref_34","unstructured":"Zhuang, J., Tang, T., Ding, Y., Tatikonda, S.C., Dvornek, N.C., Papademetris, X., and Duncan, J.S. (2020, January 6\u201312). AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients. Proceedings of the Advances in Neural Information Processing Systems, Online."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/s10915-021-01628-3","article-title":"Stochastic Gradient Descent with Polyak\u2019s Learning Rate","volume":"89","author":"Prazeres","year":"2021","journal-title":"J. Sci. Comput."},{"key":"ref_36","unstructured":"Loizou, N., Vaswani, S., Laradji, I.H., and Lacoste-Julien, S. (2021, January 13\u201315). Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence. Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, Virtual Conference."},{"key":"ref_37","unstructured":"Berrada, L., Zisserman, A., and Kumar, M.P. (2020, January 13\u201318). Training Neural Networks for and by Interpolation. Proceedings of the 37th International Conference on Machine Learning, Virtual."},{"key":"ref_38","unstructured":"Glasgow, M.R., Yuan, H., and Ma, T. (2022, January 25\u201327). Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective. Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, Virtual Conference."},{"key":"ref_39","unstructured":"Gorbunov, E., Hanzely, F., and Richt\u00e1rik, P. (2021, January 13\u201315). Local SGD: Unified Theory and New Efficient Methods. Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, Virtual Conference."},{"key":"ref_40","unstructured":"Guo, Y., Sun, Y., Hu, R., and Gong, Y. (2022, January 29\u201331). Hybrid Local SGD for Federated Learning with Heterogeneous Communications. Proceedings of the 10th International Conference on Learning Representations, Okayama, Japan."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"5511","DOI":"10.1109\/JIOT.2021.3111088","article-title":"Privacy-Preserving Asynchronous Grouped Federated Learning for IoT","volume":"9","author":"Zhang","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Zeng, T., Semiari, O., Chen, M., Saad, W., and Bennis, M. (2021, January 14\u201317). Federated Learning for Collaborative Controller Design of Connected and Autonomous Vehicles. Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC), Austin, TX, USA.","DOI":"10.1109\/CDC45484.2021.9683257"},{"key":"ref_43","unstructured":"Haddadpour, F., Kamani, M.M., Mokhtari, A., and Mahdavi, M. (2021, January 13\u201315). Federated Learning with Compression: Unified Analysis and Sharp Guarantees. Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, Virtual Conference."},{"key":"ref_44","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":"1998","journal-title":"Proc. IEEE"},{"key":"ref_45","unstructured":"Xiao, H., Rasul, K., and Vollgraf, R. (2017). Fashion-MNIST: A Novel Image Dataset for Benchmarking Machine Learning Algorithms. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/13\/6034\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:03:45Z","timestamp":1760126625000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/13\/6034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,29]]},"references-count":45,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["s23136034"],"URL":"https:\/\/doi.org\/10.3390\/s23136034","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,29]]}}}