FNNS-EC: Federated Non-performing-node-resilient Neural Selector with Energy Constraints
Bibliographic record
Abstract
Federated Learning (FL) has gained substantial popularity as a distributed machine learning framework that enhances privacy and reduce data centralization. However, FL faces several significant challenges, including non-IID data distribution among participating clients, which can degrade model performance. In addition, practical issues such as bandwidth limitations, the requirement for less frequent battery changing, and minimizing data transmissions introduce energy-related concerns that complicate FL system deployment. To address these challenges, we propose Federated Non-Performing-Node-Resilient Neural Selector with Energy Constraints (FNNS-EC), an advanced context-aware client selection algorithm that extends one of our previous works. FNNS-EC optimizes both global accuracy and energy efficiency, balancing performance with sustainability. Furthermore, we conduct extensive ablation studies, examining factors such as varying the number of clients per FL epoch, adjusting the accuracy-to-energy ratio, and testing different NonPerforming Nodes (NPNs) under various energy settings. Results, evaluated with the Selection Robustness Score (SRS), show FNNS-EC consistently outperforms baselines, demonstrating its robustness and adaptability in diverse conditions.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| 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".