GNN之节点分类任务—Cora数据集分类（半监督）

Posted 2023-03-04 小龙呀

一、数据集

       该数据集为2708个科学出版物，被分成七类。每个出版物为一个点，每个点为1433维向量，每个类别只有20个点有标注，最终要对每个点进行分类。

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

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

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'Has isolated nodes: data.has_isolated_nodes()')
print(f'Has self-loops: data.has_self_loops()') 
print(f'Is undirected: data.is_undirected()') 

train_mask，val_mask，test_mask分别表示哪些节点可用在训练集，验证集，测试集上。

二、Multi-layer Perception Network

import torch
from torch.nn import Linear
import torch.nn.functional as F
from torch_geometric.datasets import Planetoid # 下载数据集使用
from torch_geometric.transforms import NormalizeFeatures

dataset = Planetoid(root='', name='Cora', transform=NormalizeFeatures()) # transform预处理
data = dataset[0]
class MLP(torch.nn.Module):
    def __init__(self, hidden_channels):
        super().__init__()
        torch.manual_seed(1234567)
        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)

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

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

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

test_acc = test()
print(f'Test Accuracy: test_acc:.4f')

输出（部分截图）：

模型输入为1433维张量，经过为16的全连接层，输出为7维张量：

三、Graph Neural Network

import torch
import torch.nn.functional as F
from torch_geometric.nn import GCNConv
from torch_geometric.datasets import Planetoid # 下载数据集使用
from torch_geometric.transforms import NormalizeFeatures

# 可视化部分
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()

dataset = Planetoid(root='', name='Cora', transform=NormalizeFeatures()) # transform预处理
data = dataset[0]

class GCN(torch.nn.Module):
    def __init__(self, hidden_channels):
        super().__init__()
        torch.manual_seed(1234567)
        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)

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

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')

test_acc = test()
print(f'Test Accuracy: test_acc:.4f')

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

输出（部分截图）：

模型输入为1433维张量，经过为16的卷积层，输出为7维张量：

训练前二维可视化图：

训练后二维可视化图：