GCN代码分析
1 代码结构
.
├── data // 图数据
├── inits // 初始化的一些公用函数
├── layers // GCN层的定义
├── metrics // 评测指标的计算
├── models // 模型结构定义
├── train // 训练
└── utils // 工具函数的定义
utils.py
def parse_index_file(filename) # 处理index文件并返回index矩阵
def sample_mask(idx, l) #创建 mask 并返回mask矩阵
def load_data(dataset_str) # 读取数据
-
从gcn/data文件夹下读取数据，文件包括有：
-
ind.dataset_str.x => 训练实例的特征向量，如scipy.sparse.csr.csr_matrix类的实例
-
ind.dataset_str.tx => 测试实例的特征向量，如scipy.sparse.csr.csr_matrix类的实例
-
ind.dataset_str.allx => 有标签的+无无标签训练实例的特征向量，是ind.dataset_str.x的超集
-
ind.dataset_str.y => 训练实例的标签，独热编码，numpy.ndarray类的实例
-
ind.dataset_str.ty => 测试实例的标签，独热编码，numpy.ndarray类的实例
-
ind.dataset_str.ally => 有标签的+无无标签训练实例的标签，独热编码，numpy.ndarray类的实例
-
ind.dataset_str.graph => 图数据，collections.defaultdict类的实例，格式为 {index：[index_of_neighbor_nodes]}
-
ind.dataset_str.test.index => 测试实例的id
上述文件必须都用python的pickle模块存储
- 返回： adj, features, y_train, y_val, y_test, train_mask, val_mask, test_mask
def sparse_to_tuple(sparse_mx) # 将矩阵转换成tuple格式并返回
def preprocess_features(features) # 处理特征:将特征进行归一化并返回tuple (coords, values, shape)
def normalize_adj(adj) # 图归一化并返回
def preprocess_adj(adj) # 处理得到GCN中的归一化矩阵并返回
def construct_feed_dict(features, support, labels, labels_mask, placeholders) # 构建输入字典并返回
def chebyshev_polynomials(adj, k) # 切比雪夫多项式近似:计算K阶的切比雪夫近似矩阵
def chebyshev_polynomials(adj, k):
"""Calculate Chebyshev polynomials up to order k. Return a list of sparse matrices (tuple representation)."""
print("Calculating Chebyshev polynomials up to order {}...".format(k))
adj_normalized = normalize_adj(adj) # D^{-1/2}AD^{1/2}
laplacian = sp.eye(adj.shape[0]) - adj_normalized # L = I_N - D^{-1/2}AD^{1/2}
largest_eigval, _ = eigsh(laplacian, 1, which='LM') # lambda_{max}
scaled_laplacian = (2. / largest_eigval[0]) * laplacian - sp.eye(adj.shape[0]) # 2/lambda_{max}L-I_N
# 将切比雪夫多项式的 T_0(x) = 1和 T_1(x) = x 项加入到t_k中
t_k = list()
t_k.append(sp.eye(adj.shape[0]))
t_k.append(scaled_laplacian)
# 依据公式 T_n(x) = 2xT_n(x) - T_{n-1}(x) 构造递归程序，计算T_2 -> T_k项目
def chebyshev_recurrence(t_k_minus_one, t_k_minus_two, scaled_lap):
s_lap = sp.csr_matrix(scaled_lap, copy=True)
return 2 * s_lap.dot(t_k_minus_one) - t_k_minus_two
for i in range(2, k+1):
t_k.append(chebyshev_recurrence(t_k[-1], t_k[-2], scaled_laplacian))
return sparse_to_tuple(t_k)
layers.py
-
各层定义的方式与keras类似
-
定义基类 Layer
属性：name (String) => 定义了变量范围；logging (Boolean) => 打开或关闭TensorFlow直方图日志记录
方法：
__init__()(初始化)，_call()(定义计算)，__call__()(调用_call()函数)，_log_vars() -
定义Dense Layer类，继承自Layer类
-
定义GraphConvolution类，继承自Layer类。重点来看一下这个类的实现。
class GraphConvolution(Layer):
"""Graph convolution layer."""
def __init__(self, input_dim, output_dim, placeholders, dropout=0.,
sparse_inputs=False, act=tf.nn.relu, bias=False,
featureless=False, **kwargs):
super(GraphConvolution, self).__init__(**kwargs)
if dropout:
self.dropout = placeholders['dropout']
else:
self.dropout = 0.
self.act = act
self.support = placeholders['support']
self.sparse_inputs = sparse_inputs
self.featureless = featureless
self.bias = bias
# helper variable for sparse dropout
self.num_features_nonzero = placeholders['num_features_nonzero']
# 下面是定义变量，主要是通过调用utils.py中的glorot函数实现
with tf.variable_scope(self.name + '_vars'):
for i in range(len(self.support)):
self.vars['weights_' + str(i)] = glorot([input_dim, output_dim],
name='weights_' + str(i))
if self.bias:
self.vars['bias'] = zeros([output_dim], name='bias')
if self.logging:
self._log_vars()
def _call(self, inputs):
x = inputs
# dropout 设置dropout
if self.sparse_inputs:
x = sparse_dropout(x, 1-self.dropout, self.num_features_nonzero)
else:
x = tf.nn.dropout(x, 1-self.dropout)
# convolve 卷积的实现。主要是根据论文中公式Z = ilde{D}^{-1/2} ilde{A}^{-1/2}X heta实现
supports = list()
for i in range(len(self.support)):
if not self.featureless:
pre_sup = dot(x, self.vars['weights_' + str(i)],
sparse=self.sparse_inputs)
else:
pre_sup = self.vars['weights_' + str(i)]
support = dot(self.support[i], pre_sup, sparse=True)
supports.append(support)
output = tf.add_n(supports)
# bias
if self.bias:
output += self.vars['bias']
return self.act