2021-06-21

3. 模型对比

基于图神经网络的节点表征的学习遵循消息传递范式：

• 在邻居节点信息变换阶段，GCN与GAT都对邻居节点做归一化和线性变换（两个操作不分前后）；
• 在邻居节点信息聚合阶段都将变换后的邻居节点信息做求和聚合；
• 在中心节点信息变换阶段只是简单返回邻居节点信息聚合阶段的聚合结果。

GCN与GAT的区别在于邻居节点信息聚合过程中的归一化方法不同：

• 前者根据中心节点与邻居节点的度计算归一化系数，后者根据中心节点与邻居节点的相似度计算归一化系数。
• 前者的归一化方式依赖于图的拓扑结构，不同节点其自身的度不同、其邻居的度也不同，在一些应用中可能会影响泛化能力。
• 后者的归一化方式依赖于中心节点与邻居节点的相似度，相似度是训练得到的，因此不受图的拓扑结构的影响，在不同的任务中都会有较好的泛化表现。

3.1 MLP

3.1.1 加载数据

from torch_geometric.datasets import Planetoid
import torch

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
dataset = Planetoid(root='./data/', name='Cora')
data = dataset[0].to(device)

3.1.2 模型

import torch
from torch.nn import Linear
import torch.nn.functional as F

class MLP(torch.nn.Module):
    def __init__(self, hidden_channels):
        super(MLP, self).__init__()
        torch.manual_seed(12345)
        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).to(device)
criterion = torch.nn.CrossEntropyLoss()  # Define loss criterion.
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)  # Define optimizer.    
    

3.1.3 训练

def train():
    model.train()   # 训练状态
    optimizer.zero_grad()  # Clear gradients.
    out = model(data.x)  # Perform a single forward pass.
    loss = criterion(out[data.train_mask], data.y[data.train_mask])  
    	# Compute the loss solely based on the training nodes.
        
    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}')

print(model)

3.1.4 测试

def test():
    model.eval()   # 测试状态
    out = model(data.x)
    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}')

总

from torch_geometric.datasets import Planetoid
import torch

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
dataset = Planetoid(root='./data/', name='Cora')
data = dataset[0].to(device)


import torch
from torch.nn import Linear
import torch.nn.functional as F

class MLP(torch.nn.Module):
    def __init__(self, hidden_channels):
        super(MLP, self).__init__()
        torch.manual_seed(12345)
        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).to(device)
criterion = torch.nn.CrossEntropyLoss()  # Define loss criterion.
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)  # Define optimizer.    
    
    
    
def train():
    model.train()
    optimizer.zero_grad()  # Clear gradients.
    out = model(data.x)  # Perform a single forward pass.
    loss = criterion(out[data.train_mask], data.y[data.train_mask])  
    	# Compute the loss solely based on the training nodes.
        
    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}')

print(model)



def test():
    model.eval()
    out = model(data.x)
    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}')

3.2 GCN

3.2.0 可视化测试

from torch_geometric.datasets import Planetoid
import torch

# device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
device='cpu'


dataset = Planetoid(root='./data/', name='Cora')
data = dataset[0].to(device)


import matplotlib.pyplot as plt
from sklearn.manifold import TSNE
import torch
from torch.nn import Linear
import torch.nn.functional as F

def visualize(h, color):
    z = TSNE(n_components=2).fit_transform(h.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()


from torch_geometric.nn import 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).to(device)
model.eval()
out = model(data.x, data.edge_index)
visualize(out, color=data.y)


print("hello")

3.2.1 GCN模型

from torch_geometric.datasets import Planetoid
import torch

# device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
device='cpu'


dataset = Planetoid(root='./data/', name='Cora')
data = dataset[0].to(device)


import matplotlib.pyplot as plt
from sklearn.manifold import TSNE
import torch
from torch.nn import Linear
import torch.nn.functional as F

def visualize(h, color):
    z = TSNE(n_components=2).fit_transform(h.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()


from torch_geometric.nn import 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)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)
criterion = torch.nn.CrossEntropyLoss()

def train():
      model.train()
      optimizer.zero_grad()  # Clear gradients.
      out = model(data.x, data.edge_index)  # Perform a single forward pass.
      loss = criterion(out[data.train_mask], data.y[data.train_mask])  
    		# Compute the loss solely based on the training nodes.
      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, 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}')


model.eval()
out = model(data.x, data.edge_index)
visualize(out, color=data.y)

print("hello")

3.3 GAT

from torch_geometric.datasets import Planetoid
import torch

# device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
device = 'cpu'

dataset = Planetoid(root='./data/', name='Cora')
data = dataset[0].to(device)

import matplotlib.pyplot as plt
from sklearn.manifold import TSNE


def visualize(h, color):
    z = TSNE(n_components=2).fit_transform(h.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()



import torch
import torch.nn.functional as F

from torch_geometric.nn import GATConv


class GAT(torch.nn.Module):
    def __init__(self, hidden_channels):
        super(GAT, self).__init__()
        torch.manual_seed(12345)
        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).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)
criterion = torch.nn.CrossEntropyLoss()


def train():
    model.train()
    optimizer.zero_grad()  # Clear gradients.
    out = model(data.x, data.edge_index)  # Perform a single forward pass.
    loss = criterion(out[data.train_mask], data.y[data.train_mask])
    # Compute the loss solely based on the training nodes.
    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, 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}')

model.eval()
out = model(data.x, data.edge_index)
visualize(out, color=data.y)

print("hello")