Keras版的GCN代码学习

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

# Define parameters
DATASET = 'cora'  # 数据集的名称
FILTER = 'localpool'  # 'chebyshev' 采用的卷积类型
MAX_DEGREE = 2  # 最大多项式的度
SYM_NORM = True  # 是否对称正则化
NB_EPOCH = 200  # epoches的数量
PATIENCE = 10  # early stopping patience

# 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
X /= X.sum(1).reshape(-1, 1)

if FILTER == 'localpool':
    """ Local pooling filters (see 'renormalization trick' in Kipf & Welling, arXiv 2016) """
    print('Using local pooling filters...')
    A_ = preprocess_adj(A, SYM_NORM)
    support = 1
    graph = [X, A_]
    G = [Input(shape=(None, None), batch_shape=(None, None), sparse=True)]

elif FILTER == 'chebyshev':
    """ Chebyshev polynomial basis filters (Defferard et al., NIPS 2016)  """
    print('Using Chebyshev polynomial basis filters...')
    L = normalized_laplacian(A, SYM_NORM)
    L_scaled = rescale_laplacian(L)
    T_k = chebyshev_polynomial(L_scaled, MAX_DEGREE)
    support = MAX_DEGREE + 1
    graph = [X]+T_k
    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
print("x.shape1", X.shape[1])
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
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)

# Compile model
model = Model(inputs=[X_in]+G, outputs=Y)
model.summary()
model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=0.01))

# Helper variables for main training loop
wait = 0
preds = None
best_val_loss = 99999

# 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()

    # 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
    preds = model.predict(graph, batch_size=A.shape[0])
    # 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]),
          "train_acc= {:.4f}".format(train_val_acc[0]),
          "val_loss= {:.4f}".format(train_val_loss[1]),
          "val_acc= {:.4f}".format(train_val_acc[1]),
          "time= {:.4f}".format(time.time() - t))

    # Early stopping
    if train_val_loss[1] < best_val_loss:
        best_val_loss = train_val_loss[1]
        wait = 0
    else:
        if wait >= PATIENCE:
            print('Epoch {}: early stopping'.format(epoch))
            break
        wait += 1

# 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]))

util.py

from __future__ import print_function

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)}
    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)
    # fname：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))  # (2708,1435)
    # 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)  # 得到data部分 (2708,1433)去掉了第一列和最后一列
    # 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])  # 得到label部分，最后一列
    # build graph
    # 样本的id数组
    idx = np.array(idx_features_labels[:, 0], dtype=np.int32)  # 获得索引，论文的id
    # 由样本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)  # 被引用论文 引用论文
    # 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())),  # .flatten()的作用是把二维数组压平为一个一维数组
                     dtype=np.int32).reshape(edges_unordered.shape)
    print(labels.shape[0])
    print(edges)
    print(edges.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， np.ones()生成的是全为1的矩阵
    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(有向图转无向图)
    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
    a = features.todense()
    print(a)
    print(a.shape)
    return features.todense(), adj, labels  # todense的作用是返回一个矩阵（matrix）


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()
    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


def sample_mask(idx, l):
    mask = np.zeros(l)
    mask[idx] = 1
    return np.array(mask, dtype=np.bool)


def get_splits(y):
    idx_train = range(140)
    idx_val = range(200, 500)
    idx_test = range(500, 1500)
    y_train = np.zeros(y.shape, dtype=np.int32)
    y_val = np.zeros(y.shape, dtype=np.int32)
    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]
    train_mask = sample_mask(idx_train, y.shape[0])
    return y_train, y_val, y_test, idx_train, idx_val, idx_test, train_mask


def categorical_crossentropy(preds, labels):
    return np.mean(-np.log(np.extract(labels, preds)))


def accuracy(preds, labels):
    return np.mean(np.equal(np.argmax(labels, 1), np.argmax(preds, 1)))


def evaluate_preds(preds, labels, indices):

    split_loss = list()
    split_acc = list()

    for y_split, idx_split in zip(labels, indices):
        split_loss.append(categorical_crossentropy(preds[idx_split], y_split[idx_split]))
        split_acc.append(accuracy(preds[idx_split], y_split[idx_split]))

    return split_loss, split_acc


def normalized_laplacian(adj, symmetric=True):
    adj_normalized = normalize_adj(adj, symmetric)
    laplacian = sp.eye(adj.shape[0]) - adj_normalized
    return laplacian


def rescale_laplacian(laplacian):
    try:
        print('Calculating largest eigenvalue of normalized graph Laplacian...')
        largest_eigval = eigsh(laplacian, 1, which='LM', return_eigenvectors=False)[0]
    except ArpackNoConvergence:
        print('Eigenvalue calculation did not converge! Using largest_eigval=2 instead.')
        largest_eigval = 2

    scaled_laplacian = (2. / largest_eigval) * laplacian - sp.eye(laplacian.shape[0])
    return scaled_laplacian


def chebyshev_polynomial(X, k):
    """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())
    T_k.append(X)

    def chebyshev_recurrence(T_k_minus_one, T_k_minus_two, X):
        X_ = sp.csr_matrix(X, copy=True)
        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))

    return T_k


def sparse_to_tuple(sparse_mx):
    if not sp.isspmatrix_coo(sparse_mx):
        sparse_mx = sparse_mx.tocoo()
    coords = np.vstack((sparse_mx.row, sparse_mx.col)).transpose()
    values = sparse_mx.data
    shape = sparse_mx.shape
    return coords, values, shape


if __name__ == "__main__":
    load_data()

graph.py

from __future__ import print_function

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):
        # pop()函数用于删除列表中某元素，并返回该元素的值
        if 'input_shape' not in kwargs and 'input_dim' in kwargs:
            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()))