UAV-Assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysis
The development of the sixth-generation (6G) of wireless networks is driving computation toward the network edge, where Hierarchical Federated Learning (HFL) plays a pivotal role in distributing learning across edge devices. In HFL, edge devices train local models and send updates to an edge server...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Machine Learning in Communications and Networking |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10904929/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850098624468353024 |
|---|---|
| author | Ruslan Zhagypar Nour Kouzayha Hesham ElSawy Hayssam Dahrouj Tareq Y. Al-Naffouri |
| author_facet | Ruslan Zhagypar Nour Kouzayha Hesham ElSawy Hayssam Dahrouj Tareq Y. Al-Naffouri |
| author_sort | Ruslan Zhagypar |
| collection | DOAJ |
| description | The development of the sixth-generation (6G) of wireless networks is driving computation toward the network edge, where Hierarchical Federated Learning (HFL) plays a pivotal role in distributing learning across edge devices. In HFL, edge devices train local models and send updates to an edge server for local aggregation, which are then forwarded to a central server for global aggregation. However, the unreliability of communication channels at the edge and backhaul links poses a significant bottleneck for HFL-enabled systems. To address this challenge, this paper proposes an unbiased HFL algorithm for Uncrewed Aerial Vehicle (UAV)-assisted wireless networks. While applicable to terrestrial base stations (BSs), the proposed algorithm relies on UAVs for local model aggregation thanks to their ability to enhance wireless channels with lower latency and improved coverage. The proposed algorithm adjusts update weights during local and global aggregations at UAVs to mitigate the impact of unreliable channels. To quantify channel unreliability in HFL, stochastic geometry tools are employed to assess success probabilities of local and global model parameter transmissions. Incorporating these metrics aims to mitigate biases towards devices with better channel conditions in UAV-assisted networks. The paper further examines the theoretical convergence of the proposed unbiased UAV-assisted HFL algorithm under adverse channel conditions and highlights the impact of the limited battery capacity of the UAV on the efficiency of the HFL algorithm. Additionally, the algorithm facilitates optimization of system parameters such as UAV count, altitude, battery capacity, etc. The simulation results underscore the effectiveness of the proposed unbiased HFL scheme, demonstrating a 5.5% higher accuracy and approximately 85% faster convergence compared to conventional HFL algorithms. We make our code available at the following GitHub repository: <inline-formula> <tex-math notation="LaTeX">$\texttt {UAV-assisted Unbiased HFL Code}$ </tex-math></inline-formula>. |
| format | Article |
| id | doaj-art-5e77b3efe8164aaab675a80d07d1d56b |
| institution | DOAJ |
| issn | 2831-316X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Machine Learning in Communications and Networking |
| spelling | doaj-art-5e77b3efe8164aaab675a80d07d1d56b2025-08-20T02:40:40ZengIEEEIEEE Transactions on Machine Learning in Communications and Networking2831-316X2025-01-01342044710.1109/TMLCN.2025.354618110904929UAV-Assisted Unbiased Hierarchical Federated Learning: Performance and Convergence AnalysisRuslan Zhagypar0https://orcid.org/0000-0001-6393-2014Nour Kouzayha1https://orcid.org/0000-0002-0660-2737Hesham ElSawy2https://orcid.org/0000-0003-4201-6126Hayssam Dahrouj3https://orcid.org/0000-0002-0737-6372Tareq Y. Al-Naffouri4https://orcid.org/0000-0001-6955-4720Department of Electrical and Computer Engineering Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE), King Abdullah University of Science and Technology, Thuwal, Saudi ArabiaDepartment of Electrical and Computer Engineering Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE), King Abdullah University of Science and Technology, Thuwal, Saudi ArabiaSchool of Computing, Queen’s University, Kingston, ON, CanadaDepartment of Electrical Engineering, University of Sharjah, Sharjah, United Arab EmiratesDepartment of Electrical and Computer Engineering Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE), King Abdullah University of Science and Technology, Thuwal, Saudi ArabiaThe development of the sixth-generation (6G) of wireless networks is driving computation toward the network edge, where Hierarchical Federated Learning (HFL) plays a pivotal role in distributing learning across edge devices. In HFL, edge devices train local models and send updates to an edge server for local aggregation, which are then forwarded to a central server for global aggregation. However, the unreliability of communication channels at the edge and backhaul links poses a significant bottleneck for HFL-enabled systems. To address this challenge, this paper proposes an unbiased HFL algorithm for Uncrewed Aerial Vehicle (UAV)-assisted wireless networks. While applicable to terrestrial base stations (BSs), the proposed algorithm relies on UAVs for local model aggregation thanks to their ability to enhance wireless channels with lower latency and improved coverage. The proposed algorithm adjusts update weights during local and global aggregations at UAVs to mitigate the impact of unreliable channels. To quantify channel unreliability in HFL, stochastic geometry tools are employed to assess success probabilities of local and global model parameter transmissions. Incorporating these metrics aims to mitigate biases towards devices with better channel conditions in UAV-assisted networks. The paper further examines the theoretical convergence of the proposed unbiased UAV-assisted HFL algorithm under adverse channel conditions and highlights the impact of the limited battery capacity of the UAV on the efficiency of the HFL algorithm. Additionally, the algorithm facilitates optimization of system parameters such as UAV count, altitude, battery capacity, etc. The simulation results underscore the effectiveness of the proposed unbiased HFL scheme, demonstrating a 5.5% higher accuracy and approximately 85% faster convergence compared to conventional HFL algorithms. We make our code available at the following GitHub repository: <inline-formula> <tex-math notation="LaTeX">$\texttt {UAV-assisted Unbiased HFL Code}$ </tex-math></inline-formula>.https://ieeexplore.ieee.org/document/10904929/Federated learninghierarchical FLHFLstochastic geometryunbiased aggregationuncrewed aerial vehicles (UAVs) |
| spellingShingle | Ruslan Zhagypar Nour Kouzayha Hesham ElSawy Hayssam Dahrouj Tareq Y. Al-Naffouri UAV-Assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysis IEEE Transactions on Machine Learning in Communications and Networking Federated learning hierarchical FL HFL stochastic geometry unbiased aggregation uncrewed aerial vehicles (UAVs) |
| title | UAV-Assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysis |
| title_full | UAV-Assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysis |
| title_fullStr | UAV-Assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysis |
| title_full_unstemmed | UAV-Assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysis |
| title_short | UAV-Assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysis |
| title_sort | uav assisted unbiased hierarchical federated learning performance and convergence analysis |
| topic | Federated learning hierarchical FL HFL stochastic geometry unbiased aggregation uncrewed aerial vehicles (UAVs) |
| url | https://ieeexplore.ieee.org/document/10904929/ |
| work_keys_str_mv | AT ruslanzhagypar uavassistedunbiasedhierarchicalfederatedlearningperformanceandconvergenceanalysis AT nourkouzayha uavassistedunbiasedhierarchicalfederatedlearningperformanceandconvergenceanalysis AT heshamelsawy uavassistedunbiasedhierarchicalfederatedlearningperformanceandconvergenceanalysis AT hayssamdahrouj uavassistedunbiasedhierarchicalfederatedlearningperformanceandconvergenceanalysis AT tareqyalnaffouri uavassistedunbiasedhierarchicalfederatedlearningperformanceandconvergenceanalysis |