def train_step():
for step in range(1000):
with tf.GradientTape() as tape:
embedded = encoder1.call(train_graph)
# 对训练样本进行负采样生成不存在的边
train_neg_edge_index = negative_sampling(
train_graph.num_edges,
graph.num_nodes,
edge_index=train_graph.edge_index
) #不用replace=False是因为训练时可以有重复的负样本
#对正负样本进行训练
pos_edge_logits = predict_edge(embedded, train_graph.edge_index)
neg_edge_logits = predict_edge(embedded, train_neg_edge_index)
loss = compute_loss(pos_edge_logits, neg_edge_logits)
vars = tape.watched_variables()
grads = tape.gradient(loss, vars)
optimizer.apply_gradients(zip(grads, vars))
if step % 20 == 0:
auc_score = evaluate(embedded)
print("step = {}\tloss = {}\tauc_score = {}".format(
step, loss, auc_score))
from tf_geometric.utils.graph_utils import edge_train_test_split, negative_sampling
graph, (train_index, valid_index, test_index) = tfg.datasets.CoraDataset().load_data()
# undirected edges can be used for evaluation
undirected_train_edge_index, undirected_test_edge_index, _, _ = edge_train_test_split(
edge_index=graph.edge_index,
test_size=0.15
)
# use negative_sampling with replace=False to create negative edges for test
undirected_test_neg_edge_index = negative_sampling(
num_samples=undirected_test_edge_index.shape[1],
num_nodes=graph.num_nodes,
edge_index=graph.edge_index,
replace=False
)
# for training, you should convert undirected edges to directed edges for correct GCN propagation
train_graph = tfg.Graph(x=graph.x, edge_index=undirected_train_edge_index).convert_edge_to_directed()
embedding_size = 16
drop_rate = 0.2
gcn0 = tfg.layers.GCN(32, activation=tf.nn.relu)
gcn1 = tfg.layers.GCN(embedding_size)
dropout = keras.layers.Dropout(drop_rate)
#graph.edge_index.shape=(2, 10556)
#任务是通过自编码器对节点的特征维度进行编码，进而挖掘节点之间的相互关系，从而对节点间边的链接关系进行预测
#首先要将边进行分离，分离成训练集和测试集， 同时转为无向边
undirected_train_edge_index, undirected_test_edge_index, _, _ = edge_train_test_split(
edge_index=graph.edge_index,
num_nodes=graph.num_nodes,
mode='undirected',
test_size=0.15)
print(undirected_train_edge_index.shape,
undirected_test_edge_index.shape) #(2, 4486) (2, 792)
# 通过replace=False的负采样，来为测试集产生负样本（不存在的边），以满足验证评估要求
undirected_test_neg_edge_index = negative_sampling(
num_samples=undirected_test_edge_index.shape[1],
num_nodes=graph.num_nodes,
edge_index=graph.edge_index,
replace=False #不生成重复的负采样样本
) #(2, 792)
train_graph = tfg.Graph(
x=graph.x,
edge_index=undirected_train_edge_index).convert_edge_to_directed()
t_graph = tfg.Graph(x=graph.x, edge_index=undirected_train_edge_index)
#将训练图重新变回有向边，也就是把每条无向边首尾颠倒再复制一次
#print(train_graph.edge_index.shape)， (2, 8972)训练图中有8972条边，是将测试集中的边从原图中拆除后得到的
#利用图卷积编码器进行边的恢复
class Encoder(tf.keras.Model): #原始的图自编码器使用图卷积网络（GCN），基于节点的特征和边，为节点学习高阶特征
def __init__(self, rate, embedding_size):