CoauthorshipDBLP
- class dhg.data.CoauthorshipDBLP(data_root=None)[source]
Bases:
dhg.data.base.BaseData
The Co-authorship DBLP dataset is a citation network dataset for vertex classification task. More details see the HyperGCN paper.
The content of the Co-authorship DBLP dataset includes the following:
num_classes
: The number of classes: \(6\).num_vertices
: The number of vertices: \(41,302\).num_edges
: The number of edges: \(22,363\).dim_features
: The dimension of features: \(1,425\).features
: The vertex feature matrix.torch.Tensor
with size \((41,302 \times 1,425)\).edge_list
: The edge list.List
with length \(22,363\).labels
: The label list.torch.LongTensor
with size \((41,302, )\).train_mask
: The train mask.torch.BoolTensor
with size \((41,302, )\).val_mask
: The validation mask.torch.BoolTensor
with size \((41,302, )\).test_mask
: The test mask.torch.BoolTensor
with size \((41,302, )\).
- Parameters
data_root (
str
, optional) – Thedata_root
has stored the data. If set toNone
, this function will auto-download from server and save into the default direction~/.dhg/datasets/
. Defaults to None.