Edge Intelligence in the Generative Artificial Intelligence Era
Bibliographic record
Abstract
Edge intelligence (EI), by leveraging abundant edge resources and positioning AI algorithms closer to end-users, has long been considered a fundamental catalyst for the AI industry. As the AI realm shifts towards new Generative AI (GAI), EI offers a broader data source, reduced latency, and enhanced privacy protections, making it a more conducive environment for GAI advancements than cloud-based approaches. However, compared to traditional AI models, GAI challenges existing EI with its significantly larger model size, markedly intricate operations, and substantially heightened resource demands. This article delves deeply into the evolution of EI in the upcoming GAI era. Particularly, we first provide a thorough overview of challenges introduced by GAI, including escalated communication costs, greater computational demands, and intensified security and privacy concerns. We then extend the EI scope to encompass the entire lifecycle of GAI within EI, while jointly considering sensing, communication, and computation against these emerging challenges. Additionally, we spotlight key techniques designed to pave the way for the future of EI, elaborating on each of these in detail. To provide concrete insights into how EI adapts for GAI, we present two illustrative case studies: one focusing on diffusion model-based GAI fine-tuning in vehicular networks and the other highlighting large language model-based real-time inference offloading in wireless edge networks. Lastly, we outline three future research directions for EI, guided by the latest advancements in GAI.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.005 |
| Scholarly communication | 0.005 | 0.007 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.004 |
| 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".