Federated Learning Over Fully-Decoupled RAN Architecture for Two-Tier Computing Acceleration
Bibliographic record
Abstract
Two-tier computing paradigm that takes full advantage of both the end-user and the cloud computation capabilities has emerged as a promising way to deal with computationally-intensive tasks in the next generation wireless networks. For promoting the integration of the two-tier computing, federated learning (FL) provides an effective framework to enable the collaboration between the end-user and the cloud. However, the key performance metric, i.e., FL training latency, will be severely affected by the worst wireless link quality in both uplink and downlink. In this paper, aiming at accelerating the FL enabled end-cloud two-tier computing over the wireless networks, we introduce the uplink and downlink fully-decoupled radio access network (FD-RAN) architecture to enhance the minimum wireless link rate via multiple base stations (BSs) access collaboration and power management solution. First, the Lagrange dual decomposition and the binary variable relaxation methods are leveraged to obtain an optimal multiple BS access scheme for the enhancement of minimum uplink and downlink SINR. Subsequently, we exploit the successive convex approximation (SCA) algorithm to deal with the uplink power control and downlink power allocation with a proved data rate lower bound. Furthermore, considering the dynamic channel realizations, a stochastic optimization technique with a convex surrogate function is utilized to find the best end-cloud two-tier computing scheme for FL applications. Simulation results have demonstrated the effectiveness of our proposed joint multiple access collaboration and power management solution over FD-RAN for achieving a faster FL enabled two-tier computing task.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".