GWO-Boosted Multi-Attribute Client Selection for Over- The-Air Federated Learning
Bibliographic record
Abstract
Federated Learning (FL) has gained popularity across various industries due to its ability to train machine learning models without explicit sharing of sensitive data. While this paradigm offers significant advantages such as privacy preser-vation and reduced communication overhead, it also comes with several challenges such as deployment complexity and interoperability issues, particularly in heterogeneous scenarios or resource-constrained environments. Over-the-air (OTA) FL was introduced to address those challenges by sharing model updates without the need for direct device- to-device connections or cen-tralized servers. However, OTA - FL induces some issues related to increased energy consumption, wireless channel variability, and network latency. In this paper, we propose a multi-attribute client selection framework using the Grey Wolf optimizer to limit the number of participants in each round and optimize the OTA - FL process while considering the energy, delay, reliability, and fairness constraints of participating devices. We analyze the performance of our client selection approach in terms of model loss, convergence time, and overall accuracy. Our experimental results show that the proposed multi-attribute client selection can lower energy consumption by up to 43% compared to the random client selection method.
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 | 0.004 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".