Connectivity Enrichment for Decentralized Federated Learning Networks with Teleportation
Bibliographic record
Abstract
The six generation (6G) networks demand intelligent and decentralized solutions to meet dynamic service requirements and high quality-of-service expectations. Federated Learning (FL) emerges as a promising framework for collaborative machine learning in 6G, ensuring data privacy while supporting diverse artificial intelligence (AI)-driven services. Yet, extending FL to decentralized architectures, as necessitated by 6G heterogeneous and distributed environments, faces the challenge of data heterogeneity, resulting in catastrophic forgetting. Addressing this challenge is essential for realizing pervasive network intelligence in 6G. To address this problem, we analyze the impact of data distribution on the stability and efficiency of decentralized federated learning by analyzing the propagation of bias among nodes and examining the frequency of incorrect identification for each digit. In addition, we investigate how varying local model learning rates influence stability and efficiency. To enhance the convergence speed while maintaining stability, we propose to add a small number of teleportation links to reduce the average pair-wise distance, thereby enhancing connectivity and accelerating knowledge dissemination. The experimental results demonstrate the effectiveness of the proposed method.
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| 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".