Integrating Edge Intelligence and Blockchain: What, Why, and How
Bibliographic record
Abstract
Driven by an unprecedented boom in artificial intelligence (AI) and Internet of Things (IoT), edge intelligence (EI) pushes the frontier of AI from cloud to network edge, serving as a remarkable solution that unlocks the full potential of AI services. It is yet facing critical challenges in its decentralized management and security, limiting its capabilities to support services with numerous requirements. In this context, blockchain (BC) has been seen as a promising solution to tackle the above issues, and further support EI. Based on the number of citations or the relevance of emerging methods, this paper presents the results of a literature survey on the integration of EI and BC. Accordingly, we summarize the recent research efforts reported in the existing works on EI and BC. We then paint a comprehensive picture of the limitations of EI and why BC could benefit from EI. From there, we explore how BC benefits EI in terms of computing power management, data administration, and model optimization. In order to narrow the gap between immature BC and EI-amicable BC, we also probe into how to tailor BC to EI from four perspectives, including flexible consensus protocol, effective incentive, intellectuality smart contract, and scalability. Finally, some research challenges and future directions are presented. Different from existing surveys, our work focuses on the integration of EI and BC, develops some general models to help the reader build relevant optimization models in the integrated system, as well as provides detailed tutorials on implementation. We anticipate that this survey will motivate further discussions on the synergy of EI and BC, and offer some guidance in EI, BC, future networks, and other areas.
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 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.005 | 0.013 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".