全连接层对比GCN层实现论分分类

• (1)数据预处理
• (2)全连接层
• (3)将全连接层替换成GCN层
• (4)可视化展示

本文分别利用全连接层/GCN层实现对2708篇论分（论文之间有引用关系，由此引入图神经网络）进行7分类的任务，通过对比知：利用全连接层的准确率为59%，利用GCN层的准确率为81%

(1)数据预处理

from torch_geometric.datasets import Planetoid#下载数据集
from torch_geometric.transforms import NormalizeFeatures

dataset = Planetoid(root='data/Planetoid', name='Cora', transform=NormalizeFeatures())#transform预处理

print()
print(f'Dataset: {dataset}:')
print('======================')
print(f'Number of graphs: {len(dataset)}')#1个大图
print(f'Number of features: {dataset.num_features}')#每一篇论文为1433维向量
print(f'Number of classes: {dataset.num_classes}')#最终做一个7分类

data = dataset[0]  # Get the first graph object.
#Data(x=[2708, 1433], edge_index=[2, 10556], y=[2708], train_mask=[2708], val_mask=[2708], test_mask=[2708])
#2708篇论文，每一篇论文为1433维向量，2：2维，起点-终点，10556：边的数量
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'Has isolated nodes: {data.has_isolated_nodes()}')
print(f'Has self-loops: {data.has_self_loops()}')
print(f'Is undirected: {data.is_undirected()}')

结果

(2)全连接层

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

class MLP(torch.nn.Module):
    def __init__(self, hidden_channels):
        super().__init__()
        torch.manual_seed(12345)
        self.lin1 = Linear(dataset.num_features, hidden_channels)#全连接层，1433，16
        self.lin2 = Linear(hidden_channels, dataset.num_classes)#全连接层，16，7

    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)

model = MLP(hidden_channels=16)#获取模型
criterion = torch.nn.CrossEntropyLoss()  # 损失函数Define loss criterion.
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)  # 优化器Define optimizer.

def train():#训练模型
    model.train()
    optimizer.zero_grad()  # 梯度清0Clear gradients.
    out = model(data.x)  # 通过前向传播得到输出值Perform a single forward pass.
    loss = criterion(out[data.train_mask], data.y[data.train_mask])  # 用输出值和标签预测损失值，只考虑有标签的值Compute the loss solely based on the training nodes.
    loss.backward()  # 反向传播Derive gradients.
    optimizer.step()  # 梯度更新Update parameters based on gradients.
    return loss

def test():#测试
    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())  # 计算准确率，属于哪个类别的概率最大Derive ratio of correct predictions.
    return test_acc

for epoch in range(1, 201):
    loss = train()
    print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}')

结果：

准确率为：

(3)将全连接层替换成GCN层

from torch_geometric.nn import GCNConv

class GCN(torch.nn.Module):
    def __init__(self, hidden_channels):
        super().__init__()
        torch.manual_seed(1234567)
        self.conv1 = GCNConv(dataset.num_features, hidden_channels)#GCN层，1433，16
        self.conv2 = GCNConv(hidden_channels, dataset.num_classes)#GCN层，16，7

    def forward(self, x, edge_index):
        x = self.conv1(x, edge_index)#输入点和邻阶矩阵
        x = x.relu()
        x = F.dropout(x, p=0.5, training=self.training)
        x = self.conv2(x, edge_index)#传入更新后的点的特征和邻阶矩阵
        return x

model = GCN(hidden_channels=16)

训练GCN模型，代码与MLP同

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()  
    out = model(data.x, data.edge_index)  
    loss = criterion(out[data.train_mask], data.y[data.train_mask])  
    loss.backward() 
    optimizer.step()  
    return loss

def test():
    model.eval()
    out = model(data.x, data.edge_index)
    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


for epoch in range(1, 101):
    loss = train()
    print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}')

结果

准确率为：

(4)可视化展示

%matplotlib inline
import matplotlib.pyplot as plt
from sklearn.manifold import TSNE#降维的包

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()

#原始数据展示
model = GCN(hidden_channels=16)
model.eval()

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

#分类结果展示
model.eval()

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