Temporal Dual-Attention Graph Network for Popularity Prediction in MEC Networks
Bibliographic record
Abstract
Mobile Edge Caching (MEC) emerges as a key technology in communication networks to minimize latency in handling user requests for high-demand, data-intensive services. Given the storage constraints of edge servers, it becomes imperative to dynamically cache the most popular content in a highly optimized and seamless fashion. To address this critical challenge, we leverage the capabilities of Graph Neural Networks (GNNs), renowned for their proficiency in modeling intricate interdependencies among users and content, inter-user interactions, and inter-content correlations. Existing GNN-based cashing solutions failed to properly manage computational complexity of the structural learning process, but instead mainly focused on enhancing the temporal learning aspects. Since edge servers are mainly resource-limited, it is crucial to reduce the complexity of models to reduce the train and test time. The paper addresses this gap. More specifically, capitalizing on the adaptive and scalable characteristics of GNNs, we propose the Temporal Dual Graph Attention Network (TDA-GNN) for efficient content popularity prediction in MEC networks. The proposed TDA-GNN framework employs two distinct attention units, recognizing the varied significance of neighbouring nodes and edge features in shaping node embeddings. Comparative analysis against a baseline architecture reveals that the proposed TDA-GNN framework boosts cache-hit rate. These findings underscore the potential of dual-attention mechanisms to significantly enhance MEC performance, promising smoother, faster access to content for mobile users.
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 | 0.000 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".