Caching by User Preference With Delayed Feedback for Heterogeneous Cellular Networks
Bibliographic record
Abstract
The burgeoning network traffic imposes a huge burden on the network backbone. Caching popular files at the wireless network edge is promising to address the problem. In practice, file popularity is very unlikely to know in advance. Online learning algorithms are effective to learn this uncertainty in a sequential way. In each slot, the learning agent generates a caching policy (i.e., the to-be-cached files) and can observe users' feedback about the caching policy within the same slot. This method implicitly requires that all of the users are able to provide feedback promptly. However, in practice, the availability of each individual user is affected by many factors, e.g., users are moving out of the service area temporarily, or they may still consume files in the previous slots, which may result in the feedback delay. In this paper, we propose a delay-tolerant wireless caching system that takes both the feedback delay and users' availability into consideration. We frame the content caching problem as a stochastic combinatorial multi-armed bandit problem with delayed feedback and forced-to-sleep arms, and devise an intelligent caching algorithm called CFAUD to solve the problem. Also, we show that CFAUD is effective and efficient both theoretically and practically. Finally, experiments are conducted to compare the performance of the proposed algorithm with other well-known algorithms.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 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".