虽然参考引用中未直接给出PyCharm中可用的图神经网络代码示例，但可以从引用的相关内容了解到图神经网络的一些学习方向，例如GATNE、GraphSAGE、GAT等模型。以下为一个使用PyTorch Geometric库实现简单图神经网络（Graph Convolutional Network, GCN）的代码示例： ```python import torch import torch.nn.functional as F from torch_geometric.nn import GCNConv from torch_geometric.datasets import Planetoid import torch_geometric.transforms as T # 加载数据集 dataset = Planetoid(root='data/Planetoid', name='Cora', transform=T.NormalizeFeatures()) data = dataset[0] # 定义GCN模型 class GCN(torch.nn.Module): def __init__(self): super(GCN, self).__init__() self.conv1 = GCNConv(dataset.num_node_features, 16) self.conv2 = GCNConv(16, dataset.num_classes) def forward(self, data): x, edge_index = data.x, data.edge_index x = self.conv1(x, edge_index) x = F.relu(x) x = F.dropout(x, training=self.training) x = self.conv2(x, edge_index) return F.log_softmax(x, dim=1) # 初始化模型、优化器和损失函数 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = GCN().to(device) data = data.to(device) optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4) # 训练模型 model.train() for epoch in range(200): optimizer.zero_grad() out = model(data) loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask]) loss.backward() optimizer.step() # 评估模型 model.eval() pred = model(data).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()) print(f'Test Accuracy: {test_acc:.4f}') ```