UAV-Assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysis
Bibliographic record
Abstract
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:$\texttt {UAV-assisted Unbiased HFL Code}$.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".