图神经网络GNN

pou6

已于 2024-04-24 16:24:14 修改

阅读量235

点赞数 2

文章标签：神经网络 python pytorch

于 2024-04-21 21:19:01 首次发布

本文链接：https://blog.csdn.net/m0_66184663/article/details/138045611

版权

本文介绍了如何使用PyTorch和相关库如networkx和torch_geometric对KarateClub社交网络数据集进行分析，包括构建图模型、GCN层实现、以及节点嵌入的可视化。

摘要由CSDN通过智能技术生成

import torch
import networkx as nx
import matplotlib.pyplot as plt
from torch_geometric.datasets import KarateClub
from torch_geometric.utils import to_networkx
from torch.nn import Linear
from torch_geometric.nn import GCNConv


def visualize_graph(G,color):
    plt.figure(figsize=(7,7))
    plt.xticks([])
    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()



class GCN(torch.nn.Module):
    def __init__(self):
        super().__init__()
        torch.manual_seed(123)
        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)  #输入特征和邻接矩阵
        h = h.tanh()
        h = self.conv2(h,edge_index)
        h = h.tanh()
        h = self.conv3(h,edge_index)
        h = h.tanh()

        out = self.classifier(h)

        return out,h






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}')

data = dataset[0]
print(data)


edge_index = data.edge_index
print(edge_index.t())

G = to_networkx(data,to_undirected=True)
visualize_graph(G,color=data.y)


model = GCN()
print(model)

_,h = model(data.x,data.edge_index)
print(f'Embedding shape:{list(h.shape)}')

visualize_embedding(h,color=data.y)