I'm working on a node classification problem using graphSAGE. I'm new to GNN so my code is based on the tutorials of GraphSAGE with DGL for classification task [1] and [2]. This is the code that I'm using, its a 3 layer GNN with imput size 20 and output size 2 (binary classification problem):
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, n_hidden, aggregator_type))
for i in range(n_layers - 1):
self.layers.append(dglnn.SAGEConv(n_hidden, n_hidden, aggregator_type))
self.layers.append(dglnn.SAGEConv(n_hidden, n_classes, 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),)
Every time I train the model (without changing anything), the performance changes a lot, the acurracy varies between 0.45 and 0.87. How can I guarantee the reproducibility of the results? I have tried setting the pytorch seed torch.manual_seed(), numpy seed and set the drop out to 0 but the results keep varying. Is this normal or am I missing something?
