节点分类问题
数据集：Cora
包含七类学术论文，论文与论文之间存在引用和被引用的关系
数据集导入
from torch_geometric.datasets import Planetoid
from torch_geometric.transforms import NormalizeFeatures
dataset=Planetoid(root='dataset',name='Cora',transform=NormalizeFeatures())
data=dataset[0]
print(data)
Data(edge_index=[2, 10556], test_mask=[2708], train_mask=[2708], val_mask=[2708], x=[2708, 1433], y=[2708])
打印数据集信息
print()
print(f'Dataset: {dataset}:')
print('======================')
print(f'Number of graphs: {len(dataset)}')
print(f'Number of features: {dataset.num_features}')
print(f'Number of classes: {dataset.num_classes}')
data = dataset[0] # Get the first graph object.
print()
print(data)
print('======================')
# Gather some statistics about the graph.
print(f'Number of nodes: {data.num_nodes}')
print(f'Number of edges: {data.num_edges}')
print(f'Average node degree: {data.num_edges / data.num_nodes:.2f}')
print(f'Number of training nodes: {data.train_mask.sum()}')
print(f'Training node label rate: {int(data.train_mask.sum()) / data.num_nodes:.2f}')
print(f'Contains isolated nodes: {data.contains_isolated_nodes()}')
print(f'Contains self-loops: {data.contains_self_loops()}')
print(f'Is undirected: {data.is_undirected()}')
Dataset: Cora():
Number of graphs: 1
Number of features: 1433
Number of classes: 7
Data(edge_index=[2, 10556], test_mask=[2708], train_mask=[2708], val_mask=[2708], x=[2708, 1433], y=[2708])
Number of nodes: 2708
Number of edges: 10556
Average node degree: 3.90
Number of training nodes: 140
Training node label rate: 0.05
Contains isolated nodes: False
Contains self-loops: False
Is undirected: True
节点分类图打印
import matplotlib.pyplot as plt
from sklearn.manifold import TSNE
def visualize(h, color):
z = TSNE(n_components=2).fit_transform(out.detach().cpu().numpy())
plt.figure(figsize=(10,10))
plt.xticks([])
plt.yticks([])
plt.scatter(z[:, 0], z[:, 1], s=70, c=color, cmap="Set2")
plt.show()
MLP分类
import torch.nn.functional as F
import torch
from torch.nn import Linear
class MLP(torch.nn.Module):
def __init__(self,hidden_channels):
super(MLP,self).__init__()
torch.manual_seed(12345)#为GPU设置种子
self.lin1=Linear(dataset.num_features,hidden_channels)
self.lin2=Linear(hidden_channels,dataset.num_classes)
def forward(self,x):
x=self.lin1(x)
x=x.relu()
x=F.dropout(x,p=0.5,training=self.training)
x=self.lin2(x)
return x
model=MLP(hidden_channels=16)
print(model)
训练和测试
criterion = torch.nn.CrossEntropyLoss() # 交叉熵
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4) # 优化器
def train():
model.train()
optimizer.zero_grad() # 梯度清0
out = model(data.x) # x的节点表征作为输入
loss = criterion(out[data.train_mask], data.y[data.train_mask]) # 计算损失
loss.backward() # Derive gradients.
optimizer.step() # Update parameters based on gradients.
return loss
for epoch in range(1, 201):
loss = train()
print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}')
def test():
model.eval()
out=model(data.x)
pred=out.argmax(dim=1)
test_correct=pred[data.test_mask]==data.y[data.test_mask]
test_acc=int(test_correct.sum())/int(data.test_mask.sum())
return test_acc
test_acc=test()
print(f'accuracy: {test_acc:.4f}')
准确率：0.59
打印
model.eval()
out = model(data.x)
visualize(out, color=data.y)
GCN
from torch_geometric.nn import GCNConv
class GCN(torch.nn.Module):
def __init__(self,hidden_channels):
super(GCN,self).__init__()
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)
训练和测试
criterion = torch.nn.CrossEntropyLoss() # 交叉熵
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4) # 优化器
def train():
model.train()
x,edge_index=data.x,data.edge_index
optimizer.zero_grad()
out=model(x,edge_index)
loss=criterion(out[data.train_mask],data.y[data.train_mask])
loss.backward()
optimizer.step()
return loss
for epoch in range(1,201):
loss=train()
print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}')
def test():
model.eval()
out = model(data.x, data.edge_index)
pred = out.argmax(dim=1) # Use the class with highest probability.
test_correct = pred[data.test_mask] == data.y[data.test_mask] # Check against ground-truth labels.
test_acc = int(test_correct.sum()) / int(data.test_mask.sum()) # Derive ratio of correct predictions.
return test_acc
test_acc = test()
print(f'Test Accuracy: {test_acc:.4f}')
准确率：0.826
打印
model.eval()
out=model(data.x,data.edge_index)
visualize(out,color=data.y)
GAT
from torch_geometric.nn import GATConv
class GCN(torch.nn.Module):
def __init__(self,hidden_channels):
super(GAT,self).__init__()
self.conv1=GATConv(dataset.num_features,hidden_channels)
self.conv2=GATConv(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 = GAT(hidden_channels=16)
print(model)
训练和测试
criterion = torch.nn.CrossEntropyLoss() # 交叉熵
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4) # 优化器
def train():
model.train()
x,edge_index=data.x,data.edge_index
optimizer.zero_grad()
out=model(x,edge_index)
loss=criterion(out[data.train_mask],data.y[data.train_mask])
loss.backward()
optimizer.step()
return loss
for epoch in range(1,201):
loss=train()
print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}')
def test():
model.eval()
out = model(data.x, data.edge_index)
pred = out.argmax(dim=1) # Use the class with highest probability.
test_correct = pred[data.test_mask] == data.y[data.test_mask] # Check against ground-truth labels.
test_acc = int(test_correct.sum()) / int(data.test_mask.sum()) # Derive ratio of correct predictions.
return test_acc
test_acc = test()
print(f'Test Accuracy: {test_acc:.4f}')
准确率：0.755
打印
model.eval()
out=model(data.x,data.edge_index)
visualize(out,color=data.y)
总结
本次主要是学习pyg中内置的一些图网络的使用，但是想要深挖其中的原理，还是需要从源码入手，已经通过消息传递机制来构建自己的图网络。