Smart City Gnosys

Smart city article details

Title	Adaptfl: Adaptive Federated Learning Framework For Heterogeneous Devices
ID_Doc	6181
Authors	Zhang Y.; Xia H.; Xu S.; Wang X.; Xu L.
Year	2025
Published	Future Generation Computer Systems, 165
DOI	http://dx.doi.org/10.1016/j.future.2024.107610
Abstract	With the development of the Internet of Things (IoT), Federated Learning (FL) is extensively employed in smart cities and industrial IoT, involving numerous heterogeneous devices with varying computational and storage capabilities. Traditional FL assumes that clients have enough resources to train a unified global model from the beginning to the end of training. However, it ignores the problem of uneven and real-time changes in client resources. Additionally, there are aggregation difficulties between heterogeneous client models and global model. To address these challenges, we propose an Adaptive Federated Learning Framework for Heterogeneous Devices (AdaptFL). In AdaptFL, we employ a resource-aware neural architecture search method, which searches for models based on each client's resource conditions. It enables AdaptFL to automatically assign customized models tailored to each client's specific resource conditions in the current round. Additionally, we employ a staged knowledge distillation strategy to facilitate efficient distribution and aggregation between the heterogeneous global model and the client models. Experimental results demonstrate that, compared to state-of-the-art model-level heterogeneous ablation methods, AdaptFL improves global test accuracy by 4% to 15% on the SVHN dataset and enhances accuracy by 5% to 14% in scenarios with heterogeneous data. Additionally, AdaptFL effectively reduces communication overhead by over 50% across all datasets. Furthermore, it offers a degree of resilience against model poisoning attacks. © 2024 Elsevier B.V.
Author Keywords	Federated learning; Heterogeneous device; Knowledge distillation; Neural architecture search

Similar Articles

Id	Similarity	Authors	Title	Published
16069	0.903	Ni W.; Han J.; Qin Z.	Convergence Analysis Of Semi-Federated Learning With Non-Iid Data	2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Proceedings (2024)
54221	0.872	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)
26365	0.87	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)
48316	0.868	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)
26346	0.868	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)
26328	0.865	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)
924	0.864	Mehdi M.; Makkar A.; Conway M.	A Comprehensive Review Of Open-Source Federated Learning Frameworks	Procedia Computer Science, 260 (2025)
26360	0.862	Hosseini Mirmahaleh S.Y.; Rahmani A.M.	Federated Learning In Smart Cities	Model Optimization Methods for Efficient and Edge AI: Federated Learning Architectures, Frameworks and Applications (2024)
41757	0.861	Adam M.; Baroudi U.	Performance Evaluation Of Hierarchical Federated Learning On Resource-Constrained Iot Systems	IEEE Vehicular Technology Conference (2024)
1161	0.857	Kishor K.; Quezada A.; Yadav S.P.	A Critical Role For Federated Learning In Iot	Federated Learning for Smart Communication using IoT Application (2024)