CocitationCora

class dhg.data.CocitationCora(data_root=None)[source]

The Co-citation Cora dataset is a citation network dataset for vertex classification task. More details see the HyperGCN paper.

The content of the Co-citation Cora dataset includes the following:

num_classes: The number of classes: \(7\).
num_vertices: The number of vertices: \(2,708\).
num_edges: The number of edges: \(1,579\).
dim_features: The dimension of features: \(1,433\).
features: The vertex feature matrix. torch.Tensor with size \((2,708 \times 1,433)\).
edge_list: The edge list. List with length \(1,579\).
labels: The label list. torch.LongTensor with size \((2,708, )\).
train_mask: The train mask. torch.BoolTensor with size \((2,708, )\).
val_mask: The validation mask. torch.BoolTensor with size \((2,708, )\).
test_mask: The test mask. torch.BoolTensor with size \((2,708, )\).

Parameters: data_root (str, optional) – The data_root has stored the data. If set to None, this function will auto-download from server and save into the default direction ~/.dhg/datasets/. Defaults to None.