Datasets
Standard Dataset
Dataset and Code for A Graph-Neural-Network-Powered Solver Framework
- Citation Author(s):
- Submitted by:
- Congsong Zhang
- Last updated:
- Sat, 07/01/2023 - 15:54
- DOI:
- 10.21227/nzn9-td08
- Data Format:
- License:
- Categories:
- Keywords:
Abstract
The dataset referenced herein pertains to the robust framework we introduced in our scholarly article titled, "A Graph-Neural-Network-Powered Solver Framework for Graph Optimization Problems." This comprehensive dataset is categorized into three segments: training data, verification data, and test data. Each dataset plays an integral role in the functionality and optimization of the proposed framework. The training data aids in formulating the GNN model, the verification data is used for fine-tuning the model, and the test data assesses the model's performance in test scenarios. Notably, these datasets are not a static entity; they can be reproduced using the graph model outlined in our paper. This dynamism allows for continual model optimization and provides an avenue for others in the scientific community to replicate our work, thereby fostering open and reproducible research.
The dataset referenced herein pertains to the robust framework we introduced in our scholarly article titled, "A Graph-Neural-Network-Powered Solver Framework for Graph Optimization Problems." This comprehensive dataset is categorized into three segments: training data, verification data, and test data. Each dataset plays an integral role in the functionality and optimization of the proposed framework. The training data aids in formulating the GNN model, the verification data is used for fine-tuning the model, and the test data assesses the model's performance in test scenarios. Notably, these datasets are not a static entity; they can be reproduced using the graph model outlined in our paper. This dynamism allows for continual model optimization and provides an avenue for others in the scientific community to replicate our work, thereby fostering open and reproducible research.
Dataset Files
- ecc.zip (270.84 MB)
- appro_max_clique.zip (248.86 MB)
- dominating_clique.zip (1.41 GB)
- minimum_dominating_clique.zip (1.43 GB)