{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T20:50:31Z","timestamp":1785963031543,"version":"3.56.0"},"reference-count":55,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T00:00:00Z","timestamp":1650931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Huawei Technology Innovative Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Federated Learning (FL) is a privacy-preserving way to utilize the sensitive data generated by smart sensors of user devices, where a central parameter server (PS) coordinates multiple user devices to train a global model. However, relying on centralized topology poses challenges when applying FL in a sensors network, including imbalanced communication congestion and possible single point of failure, especially on the PS. To alleviate these problems, we devise a Dynamic Average Consensus-based Federated Learning (DACFL) for implementing FL in a decentralized sensors network. Different from existing studies that replace the model aggregation roughly with neighbors\u2019 average, we first transform the FL model aggregation, which is the most intractable in a decentralized topology, into the dynamic average consensus problem by treating a local training procedure as a discrete-time series.We then employ the first-order dynamic average consensus (FODAC) to estimate the average model, which not only solves the model aggregation for DACFL but also ensures model consistency as much as possible. To improve the performance with non-i.i.d data, each user also takes the neighbors\u2019 average model as its next-round initialization, which prevents the possible local over-fitting. Besides, we also provide a basic theoretical analysis of DACFL on the premise of i.i.d data. The result validates the feasibility of DACFL in both time-invariant and time-varying topologies and declares that DACFL outperforms existing studies, including CDSGD and D-PSGD, in most cases. Take the result on Fashion-MNIST as a numerical example, with i.i.d data, our DACFL achieves 19\u223c34% and 3\u223c10% increases in average accuracy; with non-i.i.d data, our DACFL achieves 30\u223c50% and 0\u223c10% increases in average accuracy, compared to CDSGD and D-PSGD.<\/jats:p>","DOI":"10.3390\/s22093317","type":"journal-article","created":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T21:37:53Z","timestamp":1651009073000},"page":"3317","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["DACFL: Dynamic Average Consensus-Based Federated Learning in Decentralized Sensors Network"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8944-7604","authenticated-orcid":false,"given":"Zhikun","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, No. 96 Jinzhai Road, Hefei 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3390-0473","authenticated-orcid":false,"given":"Daofeng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, No. 96 Jinzhai Road, Hefei 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9177-0315","authenticated-orcid":false,"given":"Jinkang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, No. 96 Jinzhai Road, Hefei 230026, China"},{"name":"PCNSS Laboratory, School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5758-2169","authenticated-orcid":false,"given":"Sihai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, No. 96 Jinzhai Road, Hefei 230026, China"},{"name":"CAS Key Laboratory of Wireless-Optical Communications, School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China"},{"name":"School of Microelectronics, University of Science and Technology of China, Hefei 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"703","DOI":"10.2501\/IJMR-2017-050","article-title":"The EU General Data Protection Regulation (GDPR): European Regulation that has a Global Impact","volume":"59","author":"Goddard","year":"2017","journal-title":"Int. J. Mark. Res."},{"key":"ref_2","first-page":"1273","article-title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","volume":"54","author":"McMahan","year":"2017","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_3","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."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.jnca.2016.11.002","article-title":"A survey on device-to-device (D2D) communication: Architecture and security issues","volume":"78","author":"Gandotra","year":"2017","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez, E., Casanova-Chafer, J., Romero, A., Vilanova, X., Mitrovics, J., and Llobet, E. (2020). LoRa Sensor Network Development for Air Quality Monitoring or Detecting Gas Leakage Events. Sensors, 20.","DOI":"10.3390\/s20216225"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Nikodem, M., Slabicki, M., and Bawiec, M. (2020). Efficient Communication Scheme for Bluetooth Low Energy in Large Scale Applications. Sensors, 20.","DOI":"10.3390\/s20216371"},{"key":"ref_7","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Collaborative Deep Learning in Fixed Topology Networks. Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_8","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent. Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_9","unstructured":"Tan, A.Z., Yu, H., Cui, L., and Yang, Q. (2022). Towards Personalized Federated Learning. IEEE Trans. Neural Netw. Learn. Syst., 1\u201317."},{"key":"ref_10","first-page":"3557","article-title":"Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach","volume":"Volume 33","author":"Larochelle","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kelli, V., Argyriou, V., Lagkas, T., Fragulis, G., Grigoriou, E., and Sarigiannidis, P. (2021). IDS for Industrial Applications: A Federated Learning Approach with Active Personalization. Sensors, 21.","DOI":"10.3390\/s21206743"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.automatica.2009.10.021","article-title":"Discrete-time dynamic average consensus","volume":"46","author":"Zhu","year":"2010","journal-title":"Automatica"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H.B., Patel, S., Ramage, D., Segal, A., and Seth, K. (November, January 30). Practical Secure Aggregation for Privacy-Preserving Machine Learning. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, Dallas, TX, USA.","DOI":"10.1145\/3133956.3133982"},{"key":"ref_14","unstructured":"Hardy, S., Henecka, W., Ivey-Law, H., Nock, R., Patrini, G., Smith, G., and Thorne, B. (2017). Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Gu, B., Deng, C., Gu, S., Bo, L., Pei, J., and Huang, H. (2021, January 14\u201318). AsySQN: Faster Vertical Federated Learning Algorithms with Better Computation Resource Utilization. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual.","DOI":"10.1145\/3447548.3467169"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e26598","DOI":"10.2196\/26598","article-title":"Implementing Vertical Federated Learning Using Autoencoders: Practical Application, Generalizability, and Utility Study","volume":"9","author":"Cha","year":"2021","journal-title":"JMIR Med. Inform."},{"key":"ref_17","first-page":"35","article-title":"Federated transfer learning: Concept and applications","volume":"15","author":"Saha","year":"2021","journal-title":"Intell. Artif."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Maurya, S., Joseph, S., Asokan, A., Algethami, A.A., Hamdi, M., and Rauf, H.T. (2021). Federated Transfer Learning for Authentication and Privacy Preservation Using Novel Supportive Twin Delayed DDPG (S-TD3) Algorithm for IIoT. Sensors, 21.","DOI":"10.3390\/s21237793"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Bowler, A.L., Pound, M.P., and Watson, N.J. (2021). Domain Adaptation and Federated Learning for Ultrasonic Monitoring of Beer Fermentation. Fermentation, 7.","DOI":"10.3390\/fermentation7040253"},{"key":"ref_20","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, Virtual."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1109\/JSAIT.2021.3054610","article-title":"Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning","volume":"2","author":"So","year":"2021","journal-title":"IEEE J. Sel. Areas Inf. Theory"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, D., Zhao, M., Zhang, S., and Zhu, J. (2020, January 25\u201328). Semi-Federated Learning. Proceedings of the 2020 IEEE Wireless Communications and Networking Conference (WCNC), Seoul, Korea.","DOI":"10.1109\/WCNC45663.2020.9120453"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Liu, L., Zhang, J., Song, S., and Letaief, K.B. (2020, January 7\u201311). Client-Edge-Cloud Hierarchical Federated Learning. Proceedings of the ICC 2020\u20142020 IEEE International Conference on Communications (ICC), Dublin, Ireland.","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"ref_24","unstructured":"Wang, H., Yurochkin, M., Sun, Y., Papailiopoulos, D., and Khazaeni, Y. (2020). Federated Learning with Matched Averaging. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Rincon, J., Julian, V., and Carrascosa, C. (2022). FLaMAS: Federated Learning Based on a SPADE MAS. Appl. Sci., 12.","DOI":"10.3390\/app12073701"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hu, K., Wu, J., Li, Y., Lu, M., Weng, L., and Xia, M. (2022). FedGCN: Federated Learning-Based Graph Convolutional Networks for Non-Euclidean Spatial Data. Mathematics, 10.","DOI":"10.3390\/math10061000"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1109\/COMST.2021.3058573","article-title":"Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems","volume":"23","author":"Wahab","year":"2021","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"102693","DOI":"10.1016\/j.jnca.2020.102693","article-title":"Blockchain for 5G and beyond networks: A state of the art survey","volume":"166","author":"Nguyen","year":"2020","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5476","DOI":"10.1109\/JIOT.2020.3030072","article-title":"A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond","volume":"8","author":"AbdulRahman","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ma, X., Liao, L., Li, Z., Lai, R.X., and Zhang, M. (2022). Applying Federated Learning in Software-Defined Networks: A Survey. Symmetry, 14.","DOI":"10.3390\/sym14020195"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Abreha, H.G., Hayajneh, M., and Serhani, M.A. (2022). Federated Learning in Edge Computing: A Systematic Survey. Sensors, 22.","DOI":"10.3390\/s22020450"},{"key":"ref_32","unstructured":"Lalitha, A., Shekhar, S., Javidi, T., and Koushanfar, F. (2018, January 7). Fully decentralized federated learning. Proceedings of the Third Workshop on Bayesian Deep Learning (NeurIPS), Montreal, QC, Canada."},{"key":"ref_33","unstructured":"Roy, A.G., Siddiqui, S., P\u00f6lsterl, S., Navab, N., and Wachinger, C. (2019). BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning. arXiv."},{"key":"ref_34","unstructured":"Wilt, M., Matelsky, J.K., and Gearhart, A.S. (2021). Scatterbrained: A flexible and expandable pattern for decentralized machine learning. arXiv."},{"key":"ref_35","unstructured":"Daily, J., Vishnu, A., Siegel, C., Warfel, T., and Amatya, V. (2018). GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descent. arXiv."},{"key":"ref_36","unstructured":"Hu, C., Jiang, J., and Wang, Z. (2019). Decentralized Federated Learning: A Segmented Gossip Approach. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Jiang, J., Hu, L., Hu, C., Liu, J., and Wang, Z. (2020). BACombo\u2014Bandwidth-Aware Decentralized Federated Learning. Electronics, 9.","DOI":"10.3390\/electronics9030440"},{"key":"ref_38","unstructured":"Pereira, J., and Ricci, L. (2019). Gossip Learning as a Decentralized Alternative to Federated Learning. Distributed Applications and Interoperable Systems, Springer International Publishing."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"5171","DOI":"10.1109\/JIOT.2020.2977383","article-title":"Decentralized Privacy Using Blockchain-Enabled Federated Learning in Fog Computing","volume":"7","author":"Qu","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, J., Hao, J., Wang, H., and Xian, M. (2020). CrowdSFL: A Secure Crowd Computing Framework Based on Blockchain and Federated Learning. Electronics, 9.","DOI":"10.3390\/electronics9050773"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1109\/MNET.011.2000263","article-title":"A Blockchain-Based Decentralized Federated Learning Framework with Committee Consensus","volume":"35","author":"Li","year":"2021","journal-title":"IEEE Netw."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"2964","DOI":"10.1109\/TII.2020.3007817","article-title":"A Blockchained Federated Learning Framework for Cognitive Computing in Industry 4.0 Networks","volume":"17","author":"Qu","year":"2021","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"12806","DOI":"10.1109\/JIOT.2021.3072611","article-title":"Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challenges","volume":"8","author":"Nguyen","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Liu, Y., Qu, Y., Xu, C., Hao, Z., and Gu, B. (2021). Blockchain-Enabled Asynchronous Federated Learning in Edge Computing. Sensors, 21.","DOI":"10.3390\/s21103335"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"2401","DOI":"10.1109\/TPDS.2021.3138848","article-title":"Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocation","volume":"33","author":"Li","year":"2022","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_46","unstructured":"Spanos, D.P., Olfati-Saber, R., and Murray, R.M. (2005, January 3\u20138). Dynamic consensus on mobile networks. Proceedings of the IFAC World Congress, Prague, Czech Republic."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Freeman, R.A., Yang, P., and Lynch, K.M. (2006, January 13\u201315). Stability and Convergence Properties of Dynamic Average Consensus Estimators. Proceedings of the 45th IEEE Conference on Decision and Control, San Diego, CA, USA.","DOI":"10.1109\/CDC.2006.377078"},{"key":"ref_48","unstructured":"Olfati-Saber, R., and Shamma, J. (2005, January 15). Consensus Filters for Sensor Networks and Distributed Sensor Fusion. Proceedings of the 44th IEEE Conference on Decision and Control, Seville, Spain."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Ren, W. (2007, January 9\u201313). Consensus Seeking in Multi-vehicle Systems with a Time-varying Reference State. Proceedings of the 2007 American Control Conference, New York, NY, USA.","DOI":"10.1109\/ACC.2007.4282230"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Yu, H., Zhang, R., Wu, J., and Li, X. (2018). Distributed Field Estimation Using Sensor Networks Based on H\u221e Consensus Filtering. Sensors, 18.","DOI":"10.3390\/s18103557"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Liu, H., Xu, B., and Liu, B. (2022). A Tracking Algorithm for Sparse and Dynamic Underwater Sensor Networks. J. Mar. Sci. Eng., 10.","DOI":"10.3390\/jmse10030337"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1137\/060659624","article-title":"The Sinkhorn\u2013Knopp Algorithm: Convergence and Applications","volume":"30","author":"Knight","year":"2008","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"ref_53","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_54","unstructured":"Xiao, H., Rasul, K., and Vollgraf, R. (2017). Fashion-MNIST: A Novel Image Dataset for Benchmarking Machine Learning Algorithms. arXiv."},{"key":"ref_55","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images, Citeseer. Technical Report."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/9\/3317\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:01:23Z","timestamp":1760137283000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/9\/3317"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,26]]},"references-count":55,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["s22093317"],"URL":"https:\/\/doi.org\/10.3390\/s22093317","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,26]]}}}