Social Network Datasets (SNDs) are structured data collected from social media platforms, online communities, or communication networks for the study of user behavior, information dissemination, community discovery, and so on. This kind of data usually contains nodes (users/entities) and edges (relationships/interactions), and is widely used in the fields of social network analysis (SNA), recommender systems, and public opinion monitoring.
1.Cora dataset is derived from a multi-group citation network, and the two-group subgraphs are selected for tasks such as graph neural network node classification. The dataset contains sparse Bag-of-Words feature vectors as node attributes, and the labels are mostly academic paper topic categories or fields. This subgraph focuses on the influence of graph structure and node characteristics on model prediction, which provides a reliable experimental benchmark for the research of multi-step adversarial attacks and defense strategies.
