Location-Dependent Task Allocation for Collaborative Mobile Users with Social Awareness
Bibliographic record
Abstract
It has been found in many areas that crowd intelligence can be exploited to effectively handle complex tasks. For instance, sensing tasks can be allocated to a group of mobile users (known as workers) to complete them efficiently. A key to success is to match tasks with workers properly so that various constraints are satisfied while a mediator for the matching can also earn a profit as an incentive for their effort. This task allocation problem has been studied in the literature from different perspectives. One aspect that is less addressed is the collaboration efficiency when a group of workers need to work together to fulfill the requirements of a task. In this paper, we attempt to solve a collaborative task allocation problem, which takes into account social connections among workers and their impact on collaboration efficiency and achievable profits. As this problem is proved to be NP-hard, we formulate a temporal heterogeneous graph and develop a deep reinforcement learning method based on an expressive neural network model for the graph. By decomposing the heterogeneous graph into smaller and simpler subgraphs, we try to reduce the network dimensionality while extracting essential features. Our experiments also show that the proposed method offers competitive advantages over other heuristic and meta-heuristic 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 | 0.001 | 0.003 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".