Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
ABSTRACT Federated learning (FL) using the federated averaging (FedAvg) algorithm has shown great advantages for large‐scale applications that rely on collaborative learning, especially when the training data is either unbalanced or inaccessible due to privacy constraints. We hypothesize that FedAvg underestimates the full extent of heterogeneity of data when the aggregation is performed. We propose Precision‐Weighted Federated Learning (PW) a novel algorithm that takes into account the second raw moment (uncentered variance) of the stochastic gradient when computing the weighted average of the parameters of independent models trained in a FL setting. With PW, we address the communication and statistical challenges for the training of distributed models with private data and provide an alternate averaging scheme that leverages the heterogeneity of the data when it has a large diversity of features in its composition. Our method was evaluated using three standard image classification datasets (MNIST, Fashion‐MNIST, and CIFAR) under two different data partitioning strategies: independent and identically distributed (IID), and nonidentical and nonindependent (non‐IID). These experiments were designed to measure the performance and efficiency of our method in resource‐constrained environments, such as mobile and IoT devices. The experimental results demonstrate that we can obtain a good balance between computational efficiency and convergence rates with PW. Our performance evaluations show better predictions with MNIST, with Fashion‐MNIST, and with CIFAR‐10 in the non‐IID setting. Further reliability evaluations ratify the stability in our method by reaching a 99% reliability index with IID partitions and 96% with non‐IID partitions. In addition, we obtained a speedup on Fashion‐MNIST with only 10 clients and up to with 100 clients participating in the aggregation concurrently per communication round. Overall, PW demonstrates improved stability and accuracy with increasing batch sizes, and it benefits significantly from lower learning rates and longer local training, compared to FedAvg and FedProx. The results indicate that PW is an effective and faster alternative approach for aggregating model updates derived from private data, especially in domains where data is highly heterogeneous.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.011 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.013 | 0.026 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it