图神经网络（三）:节点分类

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 NormalizeFeaturesdataset=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 TSNEdef 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 Linearclass 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 xmodel=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0out = 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 lossfor 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 GCNConvclass 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 xmodel = 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_indexoptimizer.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 GATConvclass 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 xmodel = 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_indexoptimizer.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。