Smart City Gnosys

Smart city article details

Title	Convergence Analysis Of Semi-Federated Learning With Non-Iid Data
ID_Doc	16069
Authors	Ni W.; Han J.; Qin Z.
Year	2024
Published	2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Proceedings
DOI	http://dx.doi.org/10.1109/ICASSPW62465.2024.10627110
Abstract	The future wireless networks are expected to support a myriad of scenarios (such as smart city, intelligent manufacturing, and remote healthcare) by utilizing the pervasive Inter-net of Things (IoT) devices (e.g., sensors, cameras, cars, and drones). However, the data distribution and the computing resource among these heterogeneous IoT devices vary widely. It is therefore very challenging to directly implement existing (centralized or federated) machine learning paradigms in such heterogeneous IoT environments. To tackle this issue, we propose a semi-federated learning (SemiFL) paradigm, which integrates centralized learning (CL) and federated learning (FL) into a generalized framework. The SemiFL framework allows computation-limited devices to participate in the learning process by transmitting their local datasets to the base station for centralized model training. To analyze the learning performance of SemiFL in heterogeneous IoT networks, we derive a convergence upper bound by quantifying the effect of learning parameters and non-IID datasets. Simulation results demonstrate that our SemiFL achieves better learning performance than FL, while reducing the communication overhead compared to conventional CL. © 2024 IEEE.
Author Keywords	Convergence analysis; heterogeneous device; Internet of Things; semi-federated learning

Similar Articles

Id	Similarity	Authors	Title	Published
48316	0.925	Albaseer A.; Abdallah M.; Al-Fuqaha A.; Erbad A.; Dobre O.A.	Semi-Supervised Federated Learning Over Heterogeneous Wireless Iot Edge Networks: Framework And Algorithms	IEEE Internet of Things Journal, 9, 24 (2022)
6181	0.903	Zhang Y.; Xia H.; Xu S.; Wang X.; Xu L.	Adaptfl: Adaptive Federated Learning Framework For Heterogeneous Devices	Future Generation Computer Systems, 165 (2025)
26346	0.89	Nguyen D.C.; Ding M.; Pathirana P.N.; Seneviratne A.; Li J.; Vincent Poor H.	Federated Learning For Internet Of Things: A Comprehensive Survey	IEEE Communications Surveys and Tutorials, 23, 3 (2021)
1161	0.883	Kishor K.; Quezada A.; Yadav S.P.	A Critical Role For Federated Learning In Iot	Federated Learning for Smart Communication using IoT Application (2024)
756	0.879	Anitha G.; Jegatheesan A.; Baburaj E.	A Comparative Analysis Of Federated Learning Towards Big Data Iot With Future Perspectives	2023 3rd International Conference on Computing and Information Technology, ICCIT 2023 (2023)
26365	0.878	Aggarwal M.; Khullar V.; Rani S.; André Prola T.; Bhattacharjee S.B.; Shawon S.M.; Goyal N.	Federated Learning On Internet Of Things: Extensive And Systematic Review	Computers, Materials and Continua, 79, 2 (2024)
54221	0.876	Yang H.; Liu H.; Yuan X.; Wu K.; Ni W.; Zhang J.A.; Liu R.P.	Synergizing Intelligence And Privacy: A Review Of Integrating Internet Of Things, Large Language Models, And Federated Learning In Advanced Networked Systems	Applied Sciences (Switzerland), 15, 12 (2025)
8396	0.874	Sharma P.; Kashniyal J.; Esham E.	An Insight Into Federated Learning: A Collaborative Approach For Machine Learning	2024 4th International Conference on Advancement in Electronics and Communication Engineering, AECE 2024 (2024)
26328	0.872	Ramadan M.N.A.; Ali M.A.H.; Khoo S.Y.; Alkhedher M.	Federated Learning And Tinyml On Iot Edge Devices: Challenges, Advances, And Future Directions	ICT Express (2025)
26356	0.87	Valente R.; Senna C.; Rito P.; Sargento S.	Federated Learning Framework To Decentralize Mobility Forecasting In Smart Cities	Proceedings of IEEE/IFIP Network Operations and Management Symposium 2023, NOMS 2023 (2023)