Graph Neural Networks

Graph neural networks (GNNs) are widely applied in graph data modeling. However, existing GNNs are often trained in a task-driven manner that fails to fully capture the intrinsic nature of the graph structure, resulting in sub-optimal node and graph representations. To address this limitation, we propose a novel \textbf{G}raph structure \textbf{P}rompt \textbf{L}earning method (GPL) to enhance the training of GNNs, which is inspired by prompt mechanisms in natural language processing.

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.

The RAHG experimental data includes six public datasets and one self-built dataset. The experimental process of RAHG on these seven datasets is also recorded in it

The RAHG experimental data includes four public datasets and one self-built dataset. The experimental process of RAHG on these five datasets is also recorded.