Long-Term Energy Management Empowered Hierarchical Federated Learning for Smart Consumer Electronics
Bibliographic record
Abstract
Managing for local data among the increasingly popular consumer smart electronics in a secure manner while increasing the user experience is still a hard work. Federated learning (FL), can develop intelligent electronics-related applications while protecting the privacy of local data. However, considering the traditional cloud-based FL training process, consumer electronics with a limited energy budget can reduce the training efficiency. Hence, in this paper, to reduce the total latency of FL training while also meeting a targeted minimum value of loss function and meeting the long-term energy consumption among smart consumer electronics, we introduce an energy-efficient hierarchical FL algorithm and formulate a multi-objective optimization problem including diversified resource allocation and device association. Considering channel state information is unavailable for all rounds, applying the Lyapunov optimization framework, an alternative problem incorporating the significance of local models is reformulated to decrease the training latency per round and enhance long-term performance at the same time. To achieve a better solution to the device association problem, a low-complexity two-operation device association algorithm is proposed, along with resource allocation for training time control, local computing power control, and bandwidth allocation. Our proposed algorithm can achieve better learning performance while meeting the energy budget compared with multiple benchmarks, according to numerical results.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".