Bibliographic record
Abstract
To address the performance degradation of federated learning (FL) under non-independent and identically distributed (non-IID) data, this study focuses on addressing label skew, one of the most common forms of non-IID heterogeneity, by implementing a Clustered Federated Learning (CFL) framework. Using Modified National Institute of Standards and Technology database (MNIST) and Canadian Institute for Advanced Research (CIFAR)-10 datasets, a warmup stage with FedAvg is first conducted to obtain an initial global model, followed by cosine similarity–based computation of client update similarity. Clients are then clustered using the K-means algorithm, and each cluster performs independent FedAvg training. The effectiveness and fairness of CFL are evaluated through global, micro, macro, and minimum accuracy metrics. Experimental results demonstrate that while FedAvg performs adequately on MNIST, it suffers from accuracy degradation on the more complex CIFAR-10 dataset. In contrast, CFL achieves higher accuracy and improved fairness by mitigating the adverse effects of non-IID distributions, showing its potential for heterogeneous federated systems.
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 | 0.008 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 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".