dgl.edge_homophily

dgl.edge_homophily(graph, y)[source]

同质性测量来自 Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs

数学上定义如下：

\[\frac{| \{ (u,v) : (u,v) \in \mathcal{E} \wedge y_u = y_v \} | } {|\mathcal{E}|},\]

其中 \(\mathcal{E}\) 是边的集合，\(y_u\) 是节点 \(u\) 的类别。

Parameters:

  • graph (DGLGraph) – The graph.

  • y (torch.Tensor) – The node labels, which is a tensor of shape (|V|).

Returns:

边缘同质性比率值。

Return type:

float

示例

>>> import dgl
>>> import torch

>>> graph = dgl.graph(([1, 2, 0, 4], [0, 1, 2, 3]))
>>> y = torch.tensor([0, 0, 0, 0, 1])
>>> dgl.edge_homophily(graph, y)
0.75