PyG框架：Graph Classification

训练GNN用来做Graph Classification

一、原理

1、根据Message Passing得到每个节点的node embedding

2、readout layer
把所有节点的node embedding聚合成整个图的graph embedding。
【文献中有很多种不同的readout layer，但最常用的是mean】

针对mini-batch，PyG框架有封装好的模块，torch_geometric.nn.global_mean_pool 可以分别将mini-batch中每个图的所有node embedding聚合成一个graph embedding（一个batch中有多少个图，就有多少个graph embedding）。一个batch的graph embedding矩阵的shape为：[batch_size，hidden_channels]。hidden_channels：一个graph embedding（向量）的长度

3、训练一个针对graph embedding的分类器

二、代码实现

PyG框架是什么？如何安装？可以参照官方文档or我的上一篇博客：https://blog.csdn.net/qq_38432089/article/details/122152640?spm=1001.2014.3001.5501
1、数据集准备

import torch
from torch_geometric.datasets import TUDataset

# 1、数据集下载
dataset = TUDataset(root='data/TUDataset', name='MUTAG')

# 查看数据集信息
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 first 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'Has isolated nodes: {data.has_isolated_nodes()}')
print(f'Has self-loops: {data.has_self_loops()}')
print(f'Is undirected: {data.is_undirected()}')

# 2、训练集、测试集准备
torch.manual_seed(12345)
dataset = dataset.shuffle()
train_dataset = dataset[:150]
test_dataset = dataset[150:]
# 训练集、测试集数量
print(f'Number of training graphs: {len(train_dataset)}')
print(f'Number of test graphs: {len(test_dataset)}')

# 3、mini-batch
from torch_geometric.loader import DataLoader

train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)

# 查看每个batch的信息：2⋅64+22=150 graphs.
for step, data in enumerate(train_loader):
    print(f'Step {step + 1}:')
    print('=======')
    print(f'Number of graphs in the current batch: {data.num_graphs}')
    print(data)
    print()

2、模型搭建

from torch.nn import Linear
import torch.nn.functional as F
from torch_geometric.nn import GCNConv
from torch_geometric.nn import global_mean_pool

class GCN(torch.nn.Module):
    def __init__(self, hidden_channels):
        super(GCN, self).__init__()
        torch.manual_seed(12345)
        self.conv1 = GCNConv(dataset.num_node_features, hidden_channels)
        self.conv2 = GCNConv(hidden_channels, hidden_channels)
        self.conv3 = GCNConv(hidden_channels, hidden_channels)
        self.lin = Linear(hidden_channels, dataset.num_classes)

    def forward(self, x, edge_index, batch):
        # 1. Obtain node embeddings 
        x = self.conv1(x, edge_index)
        x = x.relu()
        x = self.conv2(x, edge_index)
        x = x.relu()
        x = self.conv3(x, edge_index)

        # 2. Readout layer
        x = global_mean_pool(x, batch)  # [batch_size, hidden_channels]

        # 3. Apply a final classifier
        x = F.dropout(x, p=0.5, training=self.training)
        x = self.lin(x)
        
        return x

model = GCN(hidden_channels=64)
print(model)

model = GCN(hidden_channels=64)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
criterion = torch.nn.CrossEntropyLoss()

def train():
    model.train()

    for data in train_loader:  # Iterate in batches over the training dataset.
         out = model(data.x, data.edge_index, data.batch)  # Perform a single forward pass.
         loss = criterion(out, data.y)  # Compute the loss.
         loss.backward()  # Derive gradients.
         optimizer.step()  # Update parameters based on gradients.
         optimizer.zero_grad()  # Clear gradients.

def test(loader):
     model.eval()

     correct = 0
     for data in loader:  # Iterate in batches over the training/test dataset.
         out = model(data.x, data.edge_index, data.batch)  
         pred = out.argmax(dim=1)  # Use the class with highest probability.
         correct += int((pred == data.y).sum())  # Check against ground-truth labels.
     return correct / len(loader.dataset)  # Derive ratio of correct predictions.


for epoch in range(1, 171):
    train()
    train_acc = test(train_loader)
    test_acc = test(test_loader)
    print(f'Epoch: {epoch:03d}, Train Acc: {train_acc:.4f}, Test Acc: {test_acc:.4f}')

运行结果：