Decentralized Federated Learning: A Comprehensive Survey and a New Blockchain-based Data Evaluation Scheme
Bibliographic record
Abstract
Blockchain and Deep Learning (DL) are two of the most revolutionary concepts in the field of Computer Science. Both have made astounding leaps in research and application areas such as Finance, Healthcare, Internet of Things, and many more. Federated Learning (FL) is a type of distributed Deep Learning framework, in which the model is trained locally on each device and the trained gradients are sent to a central server which aggregates them and creates a global model. This helps ensure the data privacy of the user as the data never leaves the local device. However, this dependency on the central server can lead to various issues such as lack of transparency and communication bottleneck. Making this process decentralized can help address these issues. In this review, a detailed survey on using blockchain in federated learning is presented. This review also focuses on how can we use blockchain to make federated learning more transparent and decentralized to protect the privacy of the user. We also discuss the major strengths and drawbacks of each approach and further present a few ideas of our own, regarding some of these challenges and ways on how can these be improved. A new scheme to evaluate data using miners as well as methods to reduce storage overhead in decentralized federated learning are discussed in this paper.
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 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 | 0.002 | 0.022 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.018 | 0.109 |
| 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 itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
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".