本文分别利用全连接层/GCN层实现对2708篇论分进行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)
