数据链接：
官方服务：
资源简介：
Datasets appearing in "https://arxiv.org/abs/2003.00982" converted to HDF5
应用场景：
创建时间：
2021-09-11
相关数据集
StructureSAT
StructureSAT是一个大规模的饱和问题（SAT）数据集，由新南威尔士大学计算机科学与工程学院创建。该数据集包含来自不同问题领域的多样化SAT问题，旨在研究图神经网络（GNN）在SAT问题上的泛化能力。数据集涵盖了随机、设计、伪工业和工业等11个SAT领域，并研究了9种对传统SAT求解器有影响的图形结构属性。数据集通过结构属性对问题领域进行细分，以研究不同结构属性对GNN求解器泛化能力的影响
arXiv2025-02-17 更新110
GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts
The following contains the datasets described in the paper: GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts, and the associated code can be found at https://github.com/Graph-
Zenodo2023-11-06 更新50
ICPP_22_Power_Constrained_Autotuning_using_Graph_Neural_Networks
Dataset for paper submission to ICPP 22
NIAID Data Ecosystem50
Codes and datasets for AAAI 2021 paper "Learning to Pre-train Graph Neural Networks"
This record contains the dataset and codes to reproduce the published paper. Please refer to the live GitHub repository (https://github.com/rootlu/L2P-GNN) for more information. A copy of the GitHub r
DataCite Commons2022-10-25 更新100
RF-GCN_Dataset
Cora, Citeseer, and Pubmed are three citation networks for research papers, where nodes represent publications and edges denote citation links. Node attributes consist of bag-of-words representat
IEEE50
