Analysis on Optimizing Federated Proximal Algorithm for Heterogeneous and Secure Collaborative Learning
Bibliographic record
Abstract
Federated Learning (FL) has to decentralize the model training but maintains users’ data privacy, hence it is potentially essential in critical applications such as healthcare, finance, etc. For FL, the main obstacles remain the client heterogeneity and the sensitivity to any security attacks, which severely hinder its application to real scenarios. In this paper, the thesis studies the edge cases of the Federated Proximal (FedProx) algorithm that incur this phenomenon and suggests six ways for mitigating them. More precisely, the thesis considers adaptive regularization, knowledge distillation and transfer, optimization on efficiency, security defenses, client selection strategies, and approaches dealing with behavioural heterogeneity. Experiments conducted on benchmark datasets such as Canadian Institute for Advanced Research (CIFAR)-10 and Federated Extended Modified National Institute of Standards and Technology (FEMNIST) demonstrate that these strategies can improve FedProx accuracy by up to 7.2% and reduce communication rounds by up to 30%. The thesis’s findings enhance the robustness, scalability, and personalization of FedProx in heterogeneous and adversarial settings. Such enhancements have a practical benefit for implementing FL systems over various real-world settings.
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 | 0.004 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| 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".