添加自循环

class dgl.transforms.AddSelfLoop(allow_duplicate=False, new_etypes=False, edge_feat_names=None, fill_data=1.0)

Bases: BaseTransform

为图中的每个节点添加自环并返回一个新图。

对于异构图，自环仅添加到源节点类型和目标节点类型相同的边类型中。

Parameters:

• allow_duplicate (bool, optional) – 如果为False，它将首先移除自环以防止重复的自环。

• new_etypes (bool, 可选) – 如果为True，它将为每个节点类型添加一个边类型‘self’，该类型包含自环。

• edge_feat_names (list[str], optional) – 要应用fill_data的自环特征的名称。如果为None，它将应用fill_data到所有自环特征。默认值：None。

• fill_data (int, float or str, optional) –

  The value to fill the self-loop features. Default: 1.

  • If fill_data is int or float, self-loop features will be directly given by fill_data.

  • if fill_data is str, self-loop features will be generated by aggregating the features of the incoming edges of the corresponding nodes. The supported aggregation are: 'mean', 'sum', 'max', 'min'.

示例

>>> import dgl
>>> from dgl import AddSelfLoop

案例1：为同构图添加自环

>>> transform = AddSelfLoop(fill_data='sum')
>>> g = dgl.graph(([0, 0, 2], [2, 1, 0]))
>>> g.edata['he'] = torch.arange(3).float().reshape(-1, 1)
>>> new_g = transform(g)
>>> print(new_g.edges())
(tensor([0, 0, 2, 0, 1, 2]), tensor([2, 1, 0, 0, 1, 2]))
>>> print(new_g.edata('he'))
tensor([[0.],
        [1.],
        [2.],
        [2.],
        [1.],
        [0.]])

案例2：为异构图添加自环

>>> transform = AddSelfLoop(fill_data='sum')
>>> g = dgl.heterograph({
...     ('user', 'follows', 'user'): (torch.tensor([1, 2]),
...                                   torch.tensor([0, 1])),
...     ('user', 'plays', 'game'): (torch.tensor([0, 1]),
...                                 torch.tensor([0, 1]))})
>>> g.edata['feat'] = {('user', 'follows', 'user'): torch.randn(2, 5),
...                    ('user', 'plays', 'game'): torch.randn(2, 5)}
>>> g.edata['feat1'] = {('user', 'follows', 'user'): torch.randn(2, 15),
...                     ('user', 'plays', 'game'): torch.randn(2, 15)}
>>> new_g = transform(g)
>>> print(new_g.edges(etype='plays'))
(tensor([0, 1]), tensor([0, 1]))
>>> print(new_g.edges(etype='follows'))
(tensor([1, 2, 0, 1, 2]), tensor([0, 1, 0, 1, 2]))
>>> print(new_g.edata['feat'][('user', 'follows', 'user')].shape)
torch.Size([5, 5])

案例3：为异构图添加自类型

>>> transform = AddSelfLoop(new_etypes=True)
>>> new_g = transform(g)
>>> print(new_g.edges(etype='follows'))
(tensor([1, 2, 0, 1, 2]), tensor([0, 1, 0, 1, 2]))
>>> print(new_g.edges(etype=('game', 'self', 'game')))
(tensor([0, 1]), tensor([0, 1]))