直接上代码:
后面会在这份源码的基础上做实验;
TensorFlow版的GCN源码也看过了,但是看不太懂,欢迎交流GCN相关内容。
1 setup.py
from setuptools import setup
from setuptools import find_packages
setup(name='kegra', # 生成的包名称
version='0.0.1', # 版本号
description='Deep Learning on Graphs with Keras', # 包的简要描述
author='Thomas Kipf', # 包的作者
author_email='[email protected]', # 包作者的邮箱地址
url='https://tkipf.github.io', # 程序的官网地址
download_url='...', # 程序的下载地址
license='MIT', # 程序的授权信息
install_requires=['keras'], # 需要安装的依赖包
extras_require={ # 额外用于模型存储的依赖包
'model_saving': ['json', 'h5py'],
},
package_data={'kegra': ['README.md']},
# fine_packages()函数默认在和setup.py同一目录下搜索各个含有__init__.py的包
packages=find_packages())
2 utils.py
# 如果某个版本中出现了某个新的功能特性,而且这个特性和当前版本中使用的不兼容,
# 也就是说它在当前版本中不是语言标准,那么我们如果想要使用的话就要从__future__模块导入
from __future__ import print_function # print()函数
import scipy.sparse as sp # python中稀疏矩阵相关库
import numpy as np # python中操作数组的函数
from scipy.sparse.linalg.eigen.arpack import eigsh, ArpackNoConvergence # 稀疏矩阵中查找特征值/特征向量的函数
# 将标签转换为one-hot编码形式
def encode_onehot(labels):
# set()函数创建一个不重复元素集合
classes = set(labels)
# np.identity()函数创建方针,返回主对角线元素为1,其余元素为0的数组
# enumerate()函数用于将一个可遍历的数据对象(如列表、元组或字符串)组合为一个索引序列
# 同时列出数据和数据下标,一般用在for循环中
classes_dict = {c: np.identity(len(classes))[i, :] for i, c in enumerate(classes)}
# map()函数根据提供的函数对指定序列做映射
# map(function, iterable)
# 第一个参数function以参数序列中的每一个元素调用function函数,返回包含每次function函数返回值的新列表
labels_onehot = np.array(list(map(classes_dict.get, labels)), dtype=np.int32)
return labels_onehot
# 加载数据
def load_data(path="data/cora/", dataset="cora"):
"""Load citation network dataset (cora only for now)"""
# str.format()函数用于格式化字符串
print('Loading {} dataset...'.format(dataset))
# np.genfromtxt()函数用于从.csv文件或.tsv文件中生成数组
# np.genfromtxt(fname, dtype, delimiter, usecols, skip_header)
# frame:文件名
# dtype:数据类型
# delimiter:分隔符
# usecols:选择读哪几列,通常将属性集读为一个数组,将标签读为一个数组
# skip_header:是否跳过表头
idx_features_labels = np.genfromtxt("{}{}.content".format(path, dataset), dtype=np.dtype(str))
# 提取样本的特征,并将其转换为csr矩阵(压缩稀疏行矩阵),用行索引、列索引和值表示矩阵
features = sp.csr_matrix(idx_features_labels[:, 1:-1], dtype=np.float32)
# 提取样本的标签,并将其转换为one-hot编码形式
labels = encode_onehot(idx_features_labels[:, -1])
# build graph
# 样本的id数组
idx = np.array(idx_features_labels[:, 0], dtype=np.int32)
# 有样本id到样本索引的映射字典
idx_map = {j: i for i, j in enumerate(idx)}
# 样本之间的引用关系数组
edges_unordered = np.genfromtxt("{}{}.cites".format(path, dataset), dtype=np.int32)
# 将样本之间的引用关系用样本索引之间的关系表示
edges = np.array(list(map(idx_map.get, edges_unordered.flatten())),
dtype=np.int32).reshape(edges_unordered.shape)
# 构建图的邻接矩阵,用坐标形式的稀疏矩阵表示,非对称邻接矩阵
adj = sp.coo_matrix((np.ones(edges.shape[0]), (edges[:, 0], edges[:, 1])),
shape=(labels.shape[0], labels.shape[0]), dtype=np.float32)
# build symmetric adjacency matrix
# 将非对称邻接矩阵转变为对称邻接矩阵
adj = adj + adj.T.multiply(adj.T > adj) - adj.multiply(adj.T > adj)
# 打印消息:数据集有多少个节点、多少条边、每个样本有多少维特征
print('Dataset has {} nodes, {} edges, {} features.'.format(adj.shape[0], edges.shape[0], features.shape[1]))
# 返回特征的密集矩阵表示、邻接矩阵和标签的one-hot编码
return features.todense(), adj, labels
# 对邻接矩阵进行归一化处理
def normalize_adj(adj, symmetric=True):
# 如果邻接矩阵为对称矩阵,得到对称归一化邻接矩阵
# D^(-1/2) * A * D^(-1/2)
if symmetric:
# A.sum(axis=1):计算矩阵的每一行元素之和,得到节点的度矩阵D
# np.power(x, n):数组元素求n次方,得到D^(-1/2)
# sp.diags()函数根据给定的对象创建对角矩阵,对角线上的元素为给定对象中的元素
d = sp.diags(np.power(np.array(adj.sum(1)), -0.5).flatten(), 0)
# tocsr()函数将矩阵转化为压缩稀疏行矩阵
a_norm = adj.dot(d).transpose().dot(d).tocsr()
# 如果邻接矩阵不是对称矩阵,得到随机游走正则化拉普拉斯算子
# D^(-1) * A
else:
d = sp.diags(np.power(np.array(adj.sum(1)), -1).flatten(), 0)
a_norm = d.dot(adj).tocsr()
return a_norm
# 在邻接矩阵中加入自连接
def preprocess_adj(adj, symmetric=True):
adj = adj + sp.eye(adj.shape[0])
# 对加入自连接的邻接矩阵进行对称归一化处理
adj = normalize_adj(adj, symmetric)
return adj
# 构造样本掩码
def sample_mask(idx, l):
"""
:param idx: 有标签样本的索引列表
:param l: 所有样本数量
:return: 布尔类型数组,其中有标签样本所对应的位置为True,无标签样本所对应的位置为False
"""
# np.zeros()函数创建一个给定形状和类型的用0填充的数组
mask = np.zeros(l)
mask[idx] = 1
return np.array(mask, dtype=np.bool)
# 数据集划分
def get_splits(y):
# 训练集索引列表
idx_train = range(140)
# 验证集索引列表
idx_val = range(200, 500)
# 测试集索引列表
idx_test = range(500, 1500)
# 训练集样本标签
y_train = np.zeros(y.shape, dtype=np.int32)
# 验证集样本标签
y_val = np.zeros(y.shape, dtype=np.int32)
# 测试集样本标签
y_test = np.zeros(y.shape, dtype=np.int32)
y_train[idx_train] = y[idx_train]
y_val[idx_val] = y[idx_val]
y_test[idx_test] = y[idx_test]
# 训练数据的样本掩码
train_mask = sample_mask(idx_train, y.shape[0])
return y_train, y_val, y_test, idx_train, idx_val, idx_test, train_mask
# 定义分类交叉熵
def categorical_crossentropy(preds, labels):
"""
:param preds:模型对样本的输出数组
:param labels:样本的one-hot标签数组
:return:样本的平均交叉熵损失
"""
# np.extract(condition, x)函数,根据某个条件从数组中抽取元素
# np.mean()函数默认求数组中所有元素均值
return np.mean(-np.log(np.extract(labels, preds)))
# 定义准确率函数
def accuracy(preds, labels):
# np.argmax(x)函数取出x中元素最大值所对应的索引
# np.equal(x1, x2)函数用于在元素级比较两个数组是否相等
return np.mean(np.equal(np.argmax(labels, 1), np.argmax(preds, 1)))
# 评估样本划分的损失函数和准确率
def evaluate_preds(preds, labels, indices):
"""
:param preds:对于样本的预测值
:param labels:样本的标签one-hot向量
:param indices:样本的索引集合
:return:交叉熵损失函数列表、准确率列表
"""
split_loss = list()
split_acc = list()
for y_split, idx_split in zip(labels, indices):
# 计算每一个样本划分的交叉熵损失函数
split_loss.append(categorical_crossentropy(preds[idx_split], y_split[idx_split]))
# 计算每一个样本划分的准确率
split_acc.append(accuracy(preds[idx_split], y_split[idx_split]))
return split_loss, split_acc
# 对拉普拉斯矩阵进行归一化处理
def normalized_laplacian(adj, symmetric=True):
# 对称归一化的邻接矩阵,D ^ (-1/2) * A * D ^ (-1/2)
adj_normalized = normalize_adj(adj, symmetric)
# 得到对称规范化的图拉普拉斯矩阵,L = I - D ^ (-1/2) * A * D ^ (-1/2)
laplacian = sp.eye(adj.shape[0]) - adj_normalized
return laplacian
# 重新调整对称归一化的图拉普拉斯矩阵,得到其简化版本
def rescale_laplacian(laplacian):
try:
print('Calculating largest eigenvalue of normalized graph Laplacian...')
# 计算对称归一化图拉普拉斯矩阵的最大特征值
largest_eigval = eigsh(laplacian, 1, which='LM', return_eigenvectors=False)[0]
# 如果计算过程不收敛
except ArpackNoConvergence:
print('Eigenvalue calculation did not converge! Using largest_eigval=2 instead.')
largest_eigval = 2
# 调整后的对称归一化图拉普拉斯矩阵,L~ = 2 / Lambda * L - I
scaled_laplacian = (2. / largest_eigval) * laplacian - sp.eye(laplacian.shape[0])
return scaled_laplacian
# 计算直到k阶的切比雪夫多项式
def chebyshev_polynomial(X, k):
# 返回一个稀疏矩阵列表
"""Calculate Chebyshev polynomials up to order k. Return a list of sparse matrices."""
print("Calculating Chebyshev polynomials up to order {}...".format(k))
T_k = list()
T_k.append(sp.eye(X.shape[0]).tocsr()) # T0(X) = I
T_k.append(X) # T1(X) = L~
# 定义切比雪夫递归公式
def chebyshev_recurrence(T_k_minus_one, T_k_minus_two, X):
"""
:param T_k_minus_one: T(k-1)(L~)
:param T_k_minus_two: T(k-2)(L~)
:param X: L~
:return: Tk(L~)
"""
# 将输入转化为csr矩阵(压缩稀疏行矩阵)
X_ = sp.csr_matrix(X, copy=True)
# 递归公式:Tk(L~) = 2L~ * T(k-1)(L~) - T(k-2)(L~)
return 2 * X_.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], X))
# 返回切比雪夫多项式列表
return T_k
# 将稀疏矩阵转化为元组表示
def sparse_to_tuple(sparse_mx):
if not sp.isspmatrix_coo(sparse_mx):
# 将稀疏矩阵转化为coo矩阵形式
# coo矩阵采用三个数组分别存储行、列和非零元素值的信息
sparse_mx = sparse_mx.tocoo()
# np.vstack()函数沿着数组的某条轴堆叠数组
# 获取非零元素的位置索引
coords = np.vstack((sparse_mx.row, sparse_mx.col)).transpose()
# 获取矩阵的非零元素
values = sparse_mx.data
# 获取矩阵的形状
shape = sparse_mx.shape
return coords, values, shape
3 graph.py
# 如果某个版本中出现了某个新的功能特性,而且这个特性和当前版本中使用的不兼容,
# 也就是说它在当前版本中不是语言标准,那么我们如果想要使用的话就要从__future__模块导入
from __future__ import print_function # print()函数
from keras import activations, initializers, constraints
from keras import regularizers
from keras.engine import Layer
import keras.backend as K
# 定义基本的图卷积类
# Keras自定义层要实现build方法、call方法和compute_output_shape(input_shape)方法
class GraphConvolution(Layer):
"""Basic graph convolution layer as in https://arxiv.org/abs/1609.02907"""
# 构造函数
def __init__(self, units, support=1,
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
**kwargs):
if 'input_shape' not in kwargs and 'input_dim' in kwargs:
# pop()函数用于删除列表中某元素,并返回该元素的值
kwargs['input_shape'] = (kwargs.pop('input_dim'),)
super(GraphConvolution, self).__init__(**kwargs)
self.units = units
self.activation = activations.get(activation)
self.use_bias = use_bias
self.kernel_initializer = initializers.get(kernel_initializer)
self.bias_initializer = initializers.get(bias_initializer)
# 施加在权重上的正则项
self.kernel_regularizer = regularizers.get(kernel_regularizer)
# 施加在偏置向量上的正则项
self.bias_regularizer = regularizers.get(bias_regularizer)
# 施加在输出上的正则项
self.activity_regularizer = regularizers.get(activity_regularizer)
# 对主权重矩阵进行约束
self.kernel_constraint = constraints.get(kernel_constraint)
# 对偏置向量进行约束
self.bias_constraint = constraints.get(bias_constraint)
self.supports_masking = True
self.support = support
assert support >= 1
# 计算输出的形状
# 如果自定义层更改了输入张量的形状,则应该在这里定义形状变化的逻辑
# 让Keras能够自动推断各层的形状
def compute_output_shape(self, input_shapes):
# 特征矩阵形状
features_shape = input_shapes[0]
# 输出形状为(批大小, 输出维度)
output_shape = (features_shape[0], self.units)
return output_shape # (batch_size, output_dim)
# 定义层中的参数
def build(self, input_shapes):
# 特征矩阵形状
features_shape = input_shapes[0]
assert len(features_shape) == 2
# 特征维度
input_dim = features_shape[1]
self.kernel = self.add_weight(shape=(input_dim * self.support,
self.units),
initializer=self.kernel_initializer,
name='kernel',
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
# 如果存在偏置
if self.use_bias:
self.bias = self.add_weight(shape=(self.units,),
initializer=self.bias_initializer,
name='bias',
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
else:
self.bias = None
# 必须设定self.bulit = True
self.built = True
# 编写层的功能逻辑
def call(self, inputs, mask=None):
features = inputs[0] # 特征
basis = inputs[1:] # 对称归一化的邻接矩阵
# 多个图的情况
supports = list()
for i in range(self.support):
# A * X
supports.append(K.dot(basis[i], features))
# 将多个图的结果按行拼接
supports = K.concatenate(supports, axis=1)
# A * X * W
output = K.dot(supports, self.kernel)
if self.bias:
# A * X * W + b
output += self.bias
return self.activation(output)
# 定义当前层的配置信息
def get_config(self):
config = {'units': self.units,
'support': self.support,
'activation': activations.serialize(self.activation),
'use_bias': self.use_bias,
'kernel_initializer': initializers.serialize(
self.kernel_initializer),
'bias_initializer': initializers.serialize(
self.bias_initializer),
'kernel_regularizer': regularizers.serialize(
self.kernel_regularizer),
'bias_regularizer': regularizers.serialize(
self.bias_regularizer),
'activity_regularizer': regularizers.serialize(
self.activity_regularizer),
'kernel_constraint': constraints.serialize(
self.kernel_constraint),
'bias_constraint': constraints.serialize(self.bias_constraint)
}
base_config = super(GraphConvolution, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
4 train.py
from __future__ import print_function
from keras.layers import Input, Dropout
from keras.models import Model
from keras.optimizers import Adam
from keras.regularizers import l2
from kegra.layers.graph import GraphConvolution
from kegra.utils import *
import time
# 超参数
# Define parameters
DATASET = 'cora'
# 过滤器
FILTER = 'localpool' # 'chebyshev'
# 最大多项式的度
MAX_DEGREE = 2 # maximum polynomial degree
# 是否对称正则化
SYM_NORM = True # symmetric (True) vs. left-only (False) normalization
# 迭代次数
NB_EPOCH = 20000
# 提前停止参数
PATIENCE = 10 # early stopping patience
# 加载数据
# Get data
X, A, y = load_data(dataset=DATASET) # 特征、邻接矩阵、标签
# 训练集样本标签、验证集样本标签、测试集样本标签、训练集索引列表
# 验证集索引列表、测试集索引列表、训练数据的样本掩码
y_train, y_val, y_test, idx_train, idx_val, idx_test, train_mask = get_splits(y)
# 对特征进行归一化处理
# Normalize X
X /= X.sum(1).reshape(-1, 1)
# 当过滤器为局部池化过滤器时
if FILTER == 'localpool':
""" Local pooling filters (see 'renormalization trick' in Kipf & Welling, arXiv 2016) """
print('Using local pooling filters...')
# 加入自连接的邻接矩阵
A_ = preprocess_adj(A, SYM_NORM)
support = 1
# 特征矩阵和邻接矩阵
graph = [X, A_]
G = [Input(shape=(None, None), batch_shape=(None, None), sparse=True)]
# 当过滤器为切比雪夫多项式时
elif FILTER == 'chebyshev':
""" Chebyshev polynomial basis filters (Defferard et al., NIPS 2016) """
print('Using Chebyshev polynomial basis filters...')
# 对拉普拉斯矩阵进行归一化处理,得到对称规范化的拉普拉斯矩阵
L = normalized_laplacian(A, SYM_NORM)
# 重新调整对称归一化的图拉普拉斯矩阵,得到其简化版本
L_scaled = rescale_laplacian(L)
# 计算直到MAX_DEGREE阶的切比雪夫多项式
T_k = chebyshev_polynomial(L_scaled, MAX_DEGREE)
#
support = MAX_DEGREE + 1
# 特征矩阵、直到MAX_DEGREE阶的切比雪夫多项式列表
graph = [X]+T_k # 列表相加
G = [Input(shape=(None, None), batch_shape=(None, None), sparse=True) for _ in range(support)]
else:
raise Exception('Invalid filter type.')
# shape为形状元组,不包括batch_size
# 例如shape=(32, )表示预期的输入将是一批32维的向量
X_in = Input(shape=(X.shape[1],))
# 定义模型架构
# 注意:我们将图卷积网络的参数作为张量列表传递
# 更优雅的做法需要重写Layer基类
# Define model architecture
# NOTE: We pass arguments for graph convolutional layers as a list of tensors.
# This is somewhat hacky, more elegant options would require rewriting the Layer base class.
H = Dropout(0.5)(X_in)
H = GraphConvolution(16, support, activation='relu', kernel_regularizer=l2(5e-4))([H]+G)
H = Dropout(0.5)(H)
Y = GraphConvolution(y.shape[1], support, activation='softmax')([H]+G)
# 编译模型
# Compile model
model = Model(inputs=[X_in]+G, outputs=Y)
model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=0.01))
# 训练过程中的辅助变量
# Helper variables for main training loop
wait = 0
preds = None
best_val_loss = 99999
# 训练模型
# Fit
for epoch in range(1, NB_EPOCH+1):
# 统计系统时钟的时间戳
# Log wall-clock time
t = time.time()
# 每一次迭代过程
# Single training iteration (we mask nodes without labels for loss calculation)
model.fit(graph, y_train, sample_weight=train_mask, # 向sample_weight参数传递train_mask用于样本掩码
batch_size=A.shape[0], epochs=1, shuffle=False, verbose=0)
# 预测模型在整个数据集上的输出
# Predict on full dataset
preds = model.predict(graph, batch_size=A.shape[0])
# 模型在验证集上的损失和准确率
# Train / validation scores
train_val_loss, train_val_acc = evaluate_preds(preds, [y_train, y_val],
[idx_train, idx_val])
print("Epoch: {:04d}".format(epoch),
"train_loss= {:.4f}".format(train_val_loss[0]), # 在训练集上的损失
"train_acc= {:.4f}".format(train_val_acc[0]), # 在训练集上的准确率
"val_loss= {:.4f}".format(train_val_loss[1]), # 在验证集上的损失
"val_acc= {:.4f}".format(train_val_acc[1]), # 在验证集上的准确率
"time= {:.4f}".format(time.time() - t)) # 本次迭代的运行时间
# 提取停止
# Early stopping
if train_val_loss[1] < best_val_loss:
best_val_loss = train_val_loss[1]
wait = 0
else:
# 当模型在测试集上的损失连续10次迭代没有优化时,则提取停止
if wait >= PATIENCE:
print('Epoch {}: early stopping'.format(epoch))
break
wait += 1
# 模型在测试集上的损失和准确率
# Testing
test_loss, test_acc = evaluate_preds(preds, [y_test], [idx_test])
print("Test set results:",
"loss= {:.4f}".format(test_loss[0]),
"accuracy= {:.4f}".format(test_acc[0]))