An Adaptive Data Uploading Scheme for Mobile Crowdsensing via Deep Reinforcement Learning With Graph Neural Network
Bibliographic record
Abstract
Mobile crowdsensing (MCS), as an alternative to traditional sensor networks, has attracted much research attention because of its flexibility and low deployment fee. Compared with the traditional sensor networks, MCS exploits existing network infrastructures (such as edge servers and user devices) to intelligently cooperate with smart device owners. In this way, MCS combines machine intelligence and human intelligence to perform various sensing tasks more efficiently with a significantly lower cost. A challenging problem in MCS is data uploading, where mobile phone users as workers need to upload collected data to an MCS platform. In Xu and Song (2022), we proposed a heuristic approach to make a data transmission plan between mobile phone users and edge servers, which can help an MCS system leverage network resources in edge servers to facilitate data uploading efficiently. In this article, we reinvestigate the data uploading problem in Xu and Song (2022), analyze the heuristic approach’s drawbacks, and propose a deep reinforcement learning (DRL)-based method to complement these drawbacks. Specifically, we show that the heuristic approach may not sufficiently address heterogeneous cases, although it can achieve high efficiency in the homogeneous scenarios. Furthermore, we find that the heuristic method is not a one-fit-for-all method and cannot adjust itself when facing new scenarios. Instead of making a new fixed heuristic to deal with these new scenarios, we design an adaptive method based on DRL and graph neural networks (GNNs) to learn heuristics, enabling the new method to handle all possible situations in theory. Specifically, we train a DRL agent with a group of data uploading instances and then generalize the agent to other instances. Extensive numerical results show that the DRL-based approach achieves a high approximation ratio and performs stably in all sorts of experiment settings.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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; a candidate call from one teacher head, 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".