A Unified Convergence Analysis of Decentralized Federated Learning at the Edge
Bibliographic record
Abstract
Federated Learning (FL) reshapes the AI model training paradigm by enabling privacy-preserving collaborative learning, where models are trained across distributed clients without sharing raw data, but only model parameters or updates. This learning can be centralized or distributed. Centralized FL (CFL) may suffer from latency and lack of robustness due to the reliance on a coordinating server for model convergence. On the other hand, Decentralized Federated Learning (DFL) enables direct collaboration among participating devices without relying on a central server. Each device can independently connect to other devices and share model parameters. In such collaborative training paradigm, model convergence in the presence of various deployment topologies, AI model types, Non-IID data distribution, and training strategies demands systematic analysis to realize their practical deployment in critical applications such as intelligent transportation, smart factories, and real-time surveillance. Some works have attempted to conduct only partial analysis and completely neglected incorporating Non-IID data distribution, a critical factor in practical deployment of DFL in mentioned applications. This work conducts a systematic analysis on the convergence of DFL considering a wide range of AI models (e.g., classical, deep neural networks, and Large Language Models), network topologies (e.g., linear, ring, star, and mesh), training strategies (e.g., continuous and aggregate), and degree of Non-IID data distributions. The analysis includes both mathematical formulations and their implementation and evaluation using real-world data. The results confirm that the convergence rate of the models is inversely proportional to the degree of Non-IID data distribution. Moreover, judicial selection of network topologies and training strategies can aid in this convergence process for the practical edge deployment of DFL.
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 | 0.031 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.005 | 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".