Facebook

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

Bases: dhg.data.base.BaseData

The Facebook dataset is a social network dataset for vertex classification task. A page-page graph of verified Facebook sites. Nodes correspond to official Facebook pages, links to mutual likes between sites. Node features are extracted from the site descriptions. More details see the Multi-Scale Attributed Node Embedding paper.

Note

The L1-normalization for the feature is not recommended for this dataset.

The content of the Facebook dataset includes the following:

  • num_classes: The number of classes: \(4\).

  • num_vertices: The number of vertices: \(22,470\).

  • num_edges: The number of edges: \(85,501\).

  • dim_features: The dimension of features: \(4,714\).

  • features: The vertex feature matrix. torch.Tensor with size \((22,470\times 4,714)\).

  • edge_list: The edge list. List with length \((85,501 \times 2)\).

  • labels: The label list. torch.LongTensor with size \((22,470, )\).

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.