Gradient-Guided Credit Assignment and Joint Optimization for Dependency-Aware Spatial Crowdsourcing
Authors: Yafei Li, Wei Chen, Jinxing Yan, Huiling Li, Lei Gao, Mingliang Xu
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on two real-world datasets validate the effectiveness and feasibility of our proposed approach. |
| Researcher Affiliation | Academia | 1School of Computer Science and Artificial Intelligence, Zhengzhou University 2Department of Computer Science, Hong Kong Baptist University EMAIL, EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1: Meta training algorithm |
| Open Source Code | Yes | Code is available at [https://github.com/kiren-costello/dasc]. |
| Open Datasets | Yes | We extract road network data from Open Street Map1 for two cities: Chengdu (36,630 nodes, 50,786 edges) and Haikou (20,592 nodes, 49,549 edges). 1https://www.openstreetmap.org/ |
| Dataset Splits | No | The paper mentions testing on an 'experimental dataset' but does not provide specific details on how these datasets were split into training, validation, or test sets (e.g., percentages, sample counts, or methodology). |
| Hardware Specification | Yes | All experimental procedures are executed on a computational system operating Ubuntu 22.04.2 LTS with Python 3.8, equipped with Intel Core i9-13900K CPU @ 5.80 GHz, NVIDIA Ge Force RTX 3090 GPU, and 32 GB RAM. |
| Software Dependencies | Yes | All experimental procedures are executed on a computational system operating Ubuntu 22.04.2 LTS with Python 3.8 |
| Experiment Setup | Yes | We employ the SGD optimizer for training all models, utilizing a learning rate of 1 10 4. The soft update parameter is set at 1 10 3, and the hyperparameter update rate is maintained at 1 10 3. The key parameters for our simulation experiments are presented in Table 1. |