GCN实战

GCN实战

参数初始化

import time
import argparse
import numpy as np

import torch
import torch.nn.functional as F
import torch.optim as optim

from pygcn.pygcn.utils import load_data, accuracy
from pygcn.pygcn.models import GCN

# Training settings
parser = argparse.ArgumentParser()
parser.add_argument('--no-cuda', action='store_true', default=False,
                    help='Disables CUDA training.')
parser.add_argument('--fastmode', action='store_true', default=False,
                    help='Validate during training pass.')
parser.add_argument('--seed', type=int, default=42, help='Random seed.')
parser.add_argument('--epochs', type=int, default=200,
                    help='Number of epochs to train.')
parser.add_argument('--lr', type=float, default=0.01,
                    help='Initial learning rate.')
parser.add_argument('--weight_decay', type=float, default=5e-4,
                    help='Weight decay (L2 loss on parameters).')
parser.add_argument('--hidden', type=int, default=16,
                    help='Number of hidden units.')
parser.add_argument('--dropout', type=float, default=0.5,
                    help='Dropout rate (1 - keep probability).')

args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()

np.random.seed(args.seed)
torch.manual_seed(args.seed)
if args.cuda:
    torch.cuda.manual_seed(args.seed)

# MAC: option + command + <-
# Load data

加载数据

adj, features, labels, idx_train, idx_val, idx_test = load_data()

def load_data(path="../data/cora/", dataset="cora"):
    """Load citation network dataset (cora only for now)"""
    print('Loading {} dataset...'.format(dataset))

    idx_features_labels = np.genfromtxt("{}{}.content".format(path, dataset),
                                        dtype=np.dtype(str))
    features = sp.csr_matrix(idx_features_labels[:, 1:-1], dtype=np.float32)  # 取特征feature
    labels = encode_onehot(idx_features_labels[:, -1])  # one-hot label

    # build graph
    idx = np.array(idx_features_labels[:, 0], dtype=np.int32)  # 节点
    idx_map = {j: i for i, j in enumerate(idx)}   # 构建节点的索引字典
    edges_unordered = np.genfromtxt("{}{}.cites".format(path, dataset),  # 导入edge的数据
                                    dtype=np.int32)
    edges = np.array(list(map(idx_map.get, edges_unordered.flatten())),
                     dtype=np.int32).reshape(edges_unordered.shape)    # 将之前的转换成字典编号后的边
    adj = sp.coo_matrix((np.ones(edges.shape[0]), (edges[:, 0], edges[:, 1])),  # 构建边的邻接矩阵
                        shape=(labels.shape[0], labels.shape[0]),
                        dtype=np.float32)

    # build symmetric adjacency matrix，计算转置矩阵。将有向图转成无向图
    adj = adj + adj.T.multiply(adj.T > adj) - adj.multiply(adj.T > adj)

    features = normalize(features)   # 对特征做了归一化的操作
    adj = normalize(adj + sp.eye(adj.shape[0]))   # 对A+I归一化
    # 训练，验证，测试的样本
    idx_train = range(140)
    idx_val = range(200, 500)
    idx_test = range(500, 1500)
    # 将numpy的数据转换成torch格式
    features = torch.FloatTensor(np.array(features.todense()))
    labels = torch.LongTensor(np.where(labels)[1])
    adj = sparse_mx_to_torch_sparse_tensor(adj)

    idx_train = torch.LongTensor(idx_train)
    idx_val = torch.LongTensor(idx_val)
    idx_test = torch.LongTensor(idx_test)

    return adj, features, labels, idx_train, idx_val, idx_test

模型

class GraphConvolution(Module):
    """
    Simple GCN layer, similar to https://arxiv.org/abs/1609.02907
    """

    def __init__(self, in_features, out_features, bias=True):
        super(GraphConvolution, self).__init__()
        self.in_features = in_features  ## 输入特征维度
        self.out_features = out_features  ## 输出特征维度
        self.weight = Parameter(torch.FloatTensor(in_features, out_features))  # input_features, out_features
        if bias:
            self.bias = Parameter(torch.FloatTensor(out_features))
        else:
            self.register_parameter('bias', None)
        self.reset_parameters()

    def reset_parameters(self):
        stdv = 1. / math.sqrt(self.weight.size(1))
        self.weight.data.uniform_(-stdv, stdv)  # 随机化参数
        if self.bias is not None:
            self.bias.data.uniform_(-stdv, stdv)

    def forward(self, input, adj):
        support = torch.mm(input, self.weight)  # GraphConvolution forward。input*weight
        output = torch.spmm(adj, support)  # 稀疏矩阵的相乘，和mm一样的效果
        if self.bias is not None:
            return output + self.bias
        else:
            return output

    def __repr__(self):
        return self.__class__.__name__ + ' (' \
               + str(self.in_features) + ' -> ' \
               + str(self.out_features) + ')'
    
class GCN(nn.Module):
    def __init__(self, nfeat, nhid, nclass, dropout):
        super(GCN, self).__init__()

        self.gc1 = GraphConvolution(nfeat, nhid) # 构建第一层 GCN
        self.gc2 = GraphConvolution(nhid, nclass) # 构建第二层 GCN
        self.dropout = dropout

    def forward(self, x, adj):
        x = F.relu(self.gc1(x, adj))
        x = F.dropout(x, self.dropout, training=self.training)
        x = self.gc2(x, adj)
        return F.log_softmax(x, dim=1)

训练模型

# Model and optimizer,构造GCN，初始化参数。两层GCN
model = GCN(nfeat=features.shape[1],
            nhid=args.hidden,
            nclass=labels.max().item() + 1,
            dropout=args.dropout)
optimizer = optim.Adam(model.parameters(),
                       lr=args.lr, weight_decay=args.weight_decay)

if args.cuda:
    model.cuda()
    features = features.cuda()
    adj = adj.cuda()
    labels = labels.cuda()
    idx_train = idx_train.cuda()
    idx_val = idx_val.cuda()
    idx_test = idx_test.cuda()


def train(epoch):
    t = time.time()
    model.train()
    optimizer.zero_grad() # GraphConvolution forward
    output = model(features, adj)   # 运行模型，输入参数 (features, adj)
    loss_train = F.nll_loss(output[idx_train], labels[idx_train])
    acc_train = accuracy(output[idx_train], labels[idx_train])
    loss_train.backward()
    optimizer.step()

    if not args.fastmode:
        # Evaluate validation set performance separately,
        # deactivates dropout during validation run.
        model.eval()
        output = model(features, adj)

    loss_val = F.nll_loss(output[idx_val], labels[idx_val])
    acc_val = accuracy(output[idx_val], labels[idx_val])
    print('Epoch: {:04d}'.format(epoch+1),
          'loss_train: {:.4f}'.format(loss_train.item()),
          'acc_train: {:.4f}'.format(acc_train.item()),
          'loss_val: {:.4f}'.format(loss_val.item()),
          'acc_val: {:.4f}'.format(acc_val.item()),
          'time: {:.4f}s'.format(time.time() - t))


def test():
    model.eval()
    output = model(features, adj)
    loss_test = F.nll_loss(output[idx_test], labels[idx_test])
    acc_test = accuracy(output[idx_test], labels[idx_test])
    print("Test set results:",
          "loss= {:.4f}".format(loss_test.item()),
          "accuracy= {:.4f}".format(acc_test.item()))


# Train model
t_total = time.time()
for epoch in range(args.epochs):
    train(epoch)
print("Optimization Finished!")
print("Total time elapsed: {:.4f}s".format(time.time() - t_total))

# Testing
test()