Federated Learning Over Wireless Networks: Challenges and Solutions
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Motivated by ever-increasing computational resources at edge devices and increasing privacy concerns, a new machine learning (ML) framework called federated learning (FL) has been proposed. FL enables user devices, such as mobile and Internet of Things (IoT) devices, to collaboratively train an ML model by only sending the model parameters instead of raw data. FL is considered the key enabling approach for privacy-preserving, distributed ML systems. However, FL requires frequent exchange of learned model updates between multiple user devices and the cloud/edge server, which introduces a significant communication overhead and hence imposes a major challenge in FL over wireless networks that are limited in communication resources. Moreover, FL consumes a considerable amount of energy in the process of transmitting learned model updates, which imposes another challenge in FL over wireless networks that usually include unplugged devices with limited battery resources. Besides, there are still other privacy issues in practical implementations of FL over wireless networks. In this survey, we discuss each of the mentioned challenges and their respective state-of-the-art proposed solutions in an in-depth manner. By illustrating the tradeoff between each of the solutions, we discuss the underlying effect of the wireless network on the performance of FL. Finally, by highlighting the gaps between research and practical implementations, we identify future research directions for engineering FL over wireless networks.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.007 | 0.016 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it