ggfm.datasets.CiteSeer¶

class ggfm.datasets.CiteSeer(root: str | None = None, transform: Callable | None = None, pre_transform: Callable | None = None, force_reload: bool = False)[source]¶

Bases: object

The CiteSeer dataset is a widely used benchmark in graph neural network research, comprising 3,312 scientific publications in the field of computer science. These publications are categorized into six classes: Agents, AI, DB, IR, ML, and HCI. The dataset includes a citation network with 4,732 links, where each publication is represented by a 3,703-dimensional binary feature vector indicating the presence or absence of specific words in the document.