HouseCommittees

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

Bases: dhg.data.base.BaseData

The House Committees dataset is a committee network dataset for vertex classification task. In the House dataset, each node is a member of the US House of Representatives and hyperedges are formed by grouping together members of the same committee. Node labels indicate the political party of the representatives. More details see this and the YOU ARE ALLSET: A MULTISET LEARNING FRAMEWORK FOR HYPERGRAPH NEURAL NETWORKS paper.

The content of the House Committees dataset includes the following:

  • num_classes: The number of classes: \(3\).

  • num_vertices: The number of vertices: \(1,290\).

  • num_edges: The number of edges: \(341\).

  • edge_list: The edge list. List with length \(341\).

  • labels: The label list. torch.LongTensor with size \((1,290, )\).

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.