PubMed Co-Citation

The PubMed co-citation network is a hypergraph where nodes are scientific papers from the PubMed database and hyperedges are sets of papers that are co-cited together by another paper. Each node is labeled with the paper's research topic, chosen from three diabetes-related categories: Diabetes Mellitus Experimental, Diabetes Mellitus Type 1, and Diabetes Mellitus Type 2. This dataset is commonly used as a benchmark in hypergraph learning tasks, particularly for biomedical document classification.

Dataset Statistics

Nodes

Nodes

19,717

Node Type

Scientific Paper

Node Label

Research Topic

Node Degree

Min1

Q14

Median7

Q312

Max99

Node Label Distribution

Hyperedges

Hyperedges

7,963

Hyperedge Type

Co-Citation Set

Hyperedge Degree

Min2

Q12

Median3

Q34

Max171