UAV-Assisted Communication Efficient Federated Learning in the Era of the Artificial Intelligence of Things
Bibliographic record
Abstract
Artificial Intelligence (AI) based models are increasingly deployed in the Internet of Things (IoT), paving the evolution of the IoT into the AI of things (AIoT). Currently, the predominant approach for AI model training is cloud-centric and involves the sharing of data with external parties. To preserve privacy while enabling collaborative model training across distributed IoT devices, the machine learning paradigm called Federated Learning (FL) has been proposed. The future FL network is envisioned to involve up to millions of distributed IoT devices involved in collaborative learning. However, communication failures and dropouts by nodes can lead to inefficient FL. Inspired by the UAV-assisted communications in 5G heterogeneous networks (HetNet), we propose the UAV-assisted FL in this article. The FL model owner may employ UAVs to provide the intermediate model aggregation in the sky and mobile relay of the updated model parameters from data owners to the model owner. This therefore increases the reach of FL to data owners that face uncertain network conditions and improves the communication efficiency. To incentivize the UAV service providers, we adopt the multi-dimensional contract incentive design as a case study. The incentive compatibility of the contract ensures that the UAVs only choose an incentive package corresponding to its type, for example, traveling cost. The simulation results show that the UAV-assisted FL achieves significant improvement in communication efficiency and validates the incentive compatibility of our contract design.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.002 |
| 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".