如何解决使用DGL grahSAGE的GNN结果的可重复性
我正在使用graphSAGE处理节点分类问题。我是GNN的新手,所以我的代码基于带有DGL的GraphSAGE教程,用于分类任务[1]和[2]。这是我正在使用的代码,它的归类大小为20且输出大小为2(二进制分类问题)的3层GNN:
class GraphSAGE(nn.Module):
def __init__(self,in_feats,n_hidden,n_classes,n_layers,activation,dropout,aggregator_type):
super(GraphSAGE,self).__init__()
self.layers = nn.ModuleList()
self.dropout = nn.Dropout(dropout)
self.activation = activation
self.layers.append(dglnn.SAGEConv(in_feats,aggregator_type))
for i in range(n_layers - 1):
self.layers.append(dglnn.SAGEConv(n_hidden,aggregator_type))
self.layers.append(dglnn.SAGEConv(n_hidden,aggregator_type))
def forward(self,graph,inputs):
h = self.dropout(inputs)
for l,layer in enumerate(self.layers):
h = layer(graph,h)
if l != len(self.layers) - 1:
h = self.activation(h)
h = self.dropout(h)
return h
modelG = GraphSAGE(in_feats=n_features,#20
n_hidden=16,n_classes=n_labels,#2
n_layers=3,activation=F.relu,dropout=0,aggregator_type='mean')
opt = torch.optim.Adam(modelG.parameters())
for epoch in range(50):
modelG.train()
logits = modelG(g,node_features)
loss = F.cross_entropy(logits[train_mask],node_labels[train_mask])
acc = evaluate(modelG,g,node_features,node_labels,valid_mask)
opt.zero_grad()
loss.backward()
opt.step()
if epoch % 5 == 0:
print('In epoch {},loss: {}'.format(epoch,loss),)
每次我训练模型(不进行任何更改)时,性能都会发生很大变化,精确度在0.45到0.87之间变化。如何保证结果的可重复性?我尝试将pytorch种子torch.manual_seed()
设置为numpy种子,并将退出设置为0,但结果保持变化。这是正常现象还是我错过了什么?
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。