1、Cora dataset(数据集描述：Yang et al. (2016))
- 论文引用数据集，每一个点有1433维向量
- 最终要对每个点进行7分类任务(每个类别只有20个点有标注)
from torch_geometric.datasets import Planetoid#下载数据集用的
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)}')
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()}')
Dataset: Cora():
======================
Number of graphs: 1
Number of features: 1433
Number of classes: 7
Data(x=[2708, 1433], edge_index=[2, 10556], y=[2708], train_mask=[2708], val_mask=[2708], test_mask=[2708])
===========================================================================================================
Number of nodes: 2708
Number of edges: 10556
Average node degree: 3.90
Number of training nodes: 140
Training node label rate: 0.05
Has isolated nodes: False
Has self-loops: False
Is undirected: True
- val_mask和test_mask分别表示这个点需要被用到哪个集中
# 可视化部分
%matplotlib inline
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()
2、试试直接用传统的全连接层会咋样(Multi-layer Perception Network)
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)
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)
MLP(
(lin1): Linear(in_features=1433, out_features=16, bias=True)
(lin2): Linear(in_features=16, out_features=7, bias=True)
)
model = MLP(hidden_channels=16)
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, 210):
loss = train()
print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}')
Epoch: 209, Loss: 0.3570
准确率计算
test_acc = test()
print(f'Test Accuracy: {test_acc:.4f}')
Test Accuracy: 0.5890
3、Graph Neural Network (GNN)
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)
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)
GCN(
(conv1): GCNConv(1433, 16)
(conv2): GCNConv(16, 7)
)
可视化时由于输出是7维向量，所以降维成2维进行展示
model = GCN(hidden_channels=16)
model.eval()
out = model(data.x, data.edge_index)
visualize(out, color=data.y)
训练GCN模型
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}')
Epoch: 100, Loss: 0.5799
准确率计算
test_acc = test()
print(f'Test Accuracy: {test_acc:.4f}')
Test Accuracy: 0.8150
从59%到81%，这个提升还是蛮大的；训练后的可视化展示如下：
model.eval()
out = model(data.x, data.edge_index)
visualize(out, color=data.y)
