"Graph-level Classification Datasets"

"This dataset package includes three benchmark datasets (Mutagenicity, BA3-motif, and MNIST-Superpixel) designed for evaluating explainability methods of Graph Neural Networks (GNNs).Mutagenicity: 4,377 molecular graphs (avg. 30.32 nodes\/30.77 edges per graph) with 14 node features, classified into mutagenic\/non-mutagenic labels, used for molecular toxicity prediction.BA3-motif: 3,000 synthetic graphs (avg. 31.44 nodes\/31.24 edges per graph) with 5 node features, constructed by attaching house\/cycle\/grid motifs to BA base graphs, providing ground-truth subgraphs for explanation validation.MNIST-Superpixel: 70,000 graphs derived from MNIST handwritten digits (avg. 66.87 nodes\/725.39 edges per graph) with 2 node features (pixel intensity + spatial location), suitable for image-related GNN explanation tasks.All datasets are split into training (80%), validation (10%), and test (10%) sets. They support evaluating key metrics of GNN explainers (e.g., prediction accuracy, fidelity, precision) and are optimized for causal inference-driven explanation methods."

本数据集套件包含三类专为评估图神经网络（Graph Neural Networks, GNNs）可解释性方法而设计的基准数据集，分别为诱变性数据集（Mutagenicity）、BA3基序数据集（BA3-motif）以及超像素MNIST数据集（MNIST-Superpixel）。
诱变性数据集：包含4377个分子图（单图平均节点数30.32、边数30.77），具备14维节点特征，标注为诱变型与非诱变型两类，适用于分子毒性预测任务。
BA3基序数据集：包含3000个合成图（单图平均节点数31.44、边数31.24），具备5维节点特征，通过将房屋基序、环基序与网格基序附加至BA基础图中构建得到，可提供真实子图以用于可解释性验证。
超像素MNIST数据集：包含70000个由MNIST手写数字数据集衍生得到的图（单图平均节点数66.87、边数725.39），具备2维节点特征（像素强度+空间位置），适配图像相关的图神经网络可解释性任务。
所有数据集均按80%训练集、10%验证集与10%测试集的比例划分，可用于评估图神经网络可解释器的核心指标（如预测准确率、保真度、精确率），并针对因果推理驱动的可解释性方法进行了优化。