pyg的COLAB NOTEBOOKS1.Introduction: Hands-on Graph Neural Networks
原文链接：（需要梯子）
https://colab.research.google.com/drive/1h3-vJGRVloF5zStxL5I0rSy4ZUPNsjy8?usp=sharing&pli=1#scrollTo=AkQAVluLuxT_
可视化代码
# Install required packages.
import os
import torch
os.environ['TORCH'] = torch.__version__
print(torch.__version__)
!pip install -q torch-scatter -f https://data.pyg.org/whl/torch-${TORCH}.html
!pip install -q torch-sparse -f https://data.pyg.org/whl/torch-${TORCH}.html
!pip install -q git+https://github.com/pyg-team/pytorch_geometric.git
# Helper function for visualization.
%matplotlib inline
import networkx as nx
import matplotlib.pyplot as plt
def visualize_graph(G, color):
plt.figure(figsize=(7,7)) #设置幕布大小为7*7
plt.xticks([]) #默认坐标轴无刻度和标签
plt.yticks([])
nx.draw_networkx(G, pos=nx.spring_layout(G, seed=42), with_labels=False,
node_color=color, cmap="Set2")
plt.show()
def visualize_embedding(h, color, epoch=None, loss=None):
plt.figure(figsize=(7,7))
plt.xticks([])
plt.yticks([])
h = h.detach().cpu().numpy()
plt.scatter(h[:, 0], h[:, 1], s=140, c=color, cmap="Set2")
if epoch is not None and loss is not None:
plt.xlabel(f'Epoch: {epoch}, Loss: {loss.item():.4f}', fontsize=16)
plt.show()networkx.draw_networkx的使用：
draw_networkx(G, pos=None, arrows=None, with_labels=True, **kwds)
具体用法：
pos：字典（可选），以节点作为关键字，位置作为值；作用是让节点自动布局。
layout：可选，画成一个随机图，二部图或者其他；spring_layout：使用FR算法对节点进行自动布局。
seed=42：一种玄学？设置seed的目的是保证结果可复现。
导入数据库
from torch_geometric.datasets import KarateClub
dataset = KarateClub()
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}')KarateClub是一个著名的空手道俱乐部数据集，该数据集中仅有一张图即len(dataset)=1，每个节点具有一个34维的特征向量，节点根据社团内部的关系共分为四类。
观察数据
data = dataset[0] # Get the first graph object.
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()}')print(data)的输出结果是：Data(x=[34, 34], edge_index=[2, 156], y=[34], train_mask=[34])
x是34个节点，每个节点具有一个34维的特征向量；edge_index是邻接矩阵，存储格式为coo格式(coordinate format)，y是标签，
train_mask表示针对哪些节点进行训练（140个节点）。val_mask表示哪些节点用于验证，例如，用于执行早期停止（500个节点）。test_mask表示对哪些节点进行测试（1000个节点）。
。
将图可视化
from torch_geometric.utils import to_networkx
G = to_networkx(data, to_undirected=True)
visualize_graph(G, color=data.y)torch_geometric.utils.to_networkx的使用：
to_networkx(data, node_attrs=None, edge_attrs=None, graph_attrs=None, to_undirected: Union[bool, str] = False, remove_self_loops: bool = False)
作用：将torch_geometric.data.Data 类型数据转换为networkx.Graph，如果 to_undirected是True的话，就是无向图，否则反之。
搭建GCN框架
import torch
from torch.nn import Linear
from torch_geometric.nn import GCNConv
class GCN(torch.nn.Module):
def __init__(self):
super().__init__()
torch.manual_seed(1234)
# torch.manual_seed：设置CPU生成随机数的种子，方便下次复现实验结果
self.conv1 = GCNConv(dataset.num_features, 4)
self.conv2 = GCNConv(4, 4)
self.conv3 = GCNConv(4, 2)
self.classifier = Linear(2, dataset.num_classes)
def forward(self, x, edge_index):
h = self.conv1(x, edge_index)
h = h.tanh()
h = self.conv2(h, edge_index)
h = h.tanh()
h = self.conv3(h, edge_index)
h = h.tanh() # Final GNN embedding space.
# Apply a final (linear) classifier.
out = self.classifier(h)
return out, h
model = GCN()
print(model)GCN层公式原理：
该网络模型使用了三层的GCN，聚合了三跳的邻域信息，同时，GCN层也将节点特征的维度降到2，34-->4-->4-->2。最后使用线形层作为分类器，将所有节点分为四类。
该模型返回的是分类器分类结果，即一个shape为[34, 4]的矩阵，同时也返回节点的特征向量矩阵。
将降维后的特征向量可视化
model = GCN()
_, h = model(data.x, data.edge_index)
#_,是什么意思呢？
print(f'Embedding shape: {list(h.shape)}')
visualize_embedding(h, color=data.y)降维后的向量可自动聚类，说明 GNNs introduce a strong inductive bias, leading to similar embeddings for nodes that are close to each other in the input graph.
Karate Club Network的训练
import time
from IPython.display import Javascript # Restrict height of output cell.
display(Javascript('''google.colab.output.setIframeHeight(0, true, {maxHeight: 430})'''))
model = GCN()
criterion = torch.nn.CrossEntropyLoss() # Define loss criterion.
optimizer = torch.optim.Adam(model.parameters(), lr=0.01) # Define optimizer.
def train(data):
optimizer.zero_grad() # Clear gradients.
out, h = model(data.x, data.edge_index) # 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, h
for epoch in range(401):
loss, h = train(data)
if epoch % 10 == 0:
visualize_embedding(h, color=data.y, epoch=epoch, loss=loss)
time.sleep(0.3)这里：使用的损失函数是crossentroyloss，使用的优化器是Adam，
训练的流程：zero the parameter gradients + forward + backward + optimize
梯度清零+前向传播+反向传播+优化