The Cora dataset consists of 2708 scientific publications classified into one of seven classes. The citation network consists of 5429 links. Each publication in the dataset is described by a 0/1-valued word vector indicating the absence/presence of the corresponding word from the dictionary. The dictionary consists of 1433 unique words.
Source: https://relational.fit.cvut.cz/dataset/CORA
Image Source: https://arxiv.org/abs/1611.08402
Variants: Cora (weighted evaluation), Cora: fixed 5 node per class, Cora: fixed 20 node per class, Cora: fixed 10 node per class, Cora random partition, Cora Full-supervised, Cora (nonstandard variant), Cora (biased evaluation), Cora with Public Split: fixed 20 nodes per class, Cora (3%), Cora (1%), Cora (0.5%), Cora
This dataset is used in 6 benchmarks:
Recent papers with results on this dataset: