Federated Learning Games in Internet of Edges
Bibliographic record
Abstract
In 6G, the network is envisioned as a service embedded within a unified digital infrastructure that also provides computing, storage, and control. This infrastructure spans both horizontal and vertical planes and integrates with the Cloud Continuum, including edge data centers. The Internet of Edges aims to deploy 6G nodes with embedded micro data centers, forming a distributed edge cloud positioned near end-users or within terminal devices. Computing task requests are handled at the end-users whenever possible; otherwise, they are escalated hierarchically to higher layers. This paper addresses the challenge of identifying the best layer at which Resource-Intensive computation is to be processed, especially computation related to Machine Learning (ML) tasks. In particular, Federated Learning (FL) will enable edge devices to collaboratively train ML models while preserving data privacy. However, constrained devices face challenges such as high prediction errors due to limited dataset sizes and energy consumption cost associated with FL. To address these issues, this paper proposes to adequately characterise the computing placement depending on the device characteristics. More energy constraint devices need to choose between local learning (on device) or federated learning through an edge server. Conversely, devices doted with more capacity need to federate the ML cooperatively in learning coalitions. Both cases will be considered through the lens of game theory. Extensive numerical results highlight the effectiveness of our approach, showcasing its ability to enhance learning while minimizing energy cost.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 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".