图形神经网络回归

Question

我正在尝试在图神经网络上实现回归。我看到的大多数例子都是这一领域的分类，到目前为止还没有回归的例子。我看到一个分类如下：从torch_geometry.nn导入GCNConv

class GCN(torch.nn.Module):
def __init__(self, hidden_channels):
super(GCN, self).__init__()
torch.manual_seed(12345)
self.conv1 = GCNConv(dataset.num_features, hidden_channels)
self.conv2 = GCNConv(hidden_channels, dataset.num_classes)
def forward(self, x, edge_index):
x = self.conv1(x, edge_index)
x = x.relu()
x = F.dropout(x, p=0.5, training=self.training)
x = self.conv2(x, edge_index)
return x
model = GCN(hidden_channels=16)
print(model)

我正在尝试为我的任务修改它，这基本上包括在一个有30个节点的网络上执行回归，每个节点有3个特征，边缘有一个特征。

如果有人能给我举一些同样的例子，那将非常有帮助。

Answer 1

添加一个线性层，不要忘记使用回归损失函数

class GCN(torch.nn.Module):
def __init__(self, hidden_channels):
super(GCN, self).__init__()
torch.manual_seed(12345)
self.conv1 = GCNConv(dataset.num_features, hidden_channels)
self.conv2 = GCNConv(hidden_channels, dataset.num_classes)
self.linear1 = torch.nn.Linear(100,1)
def forward(self, x, edge_index):
x = self.conv1(x, edge_index)
x = x.relu()
x = F.dropout(x, p=0.5, training=self.training)
x = self.conv2(x, edge_index)
x = self.linear1(x)
return x