diff --git a/constructor.py b/constructor.py index e54aaaa..a4f3159 100644 --- a/constructor.py +++ b/constructor.py @@ -99,7 +99,7 @@ def format_data(data_name): print('norm is:', norm) for item in items: - #item_name = [ k for k,v in locals().iteritems() if v == item][0] + # item_name = [ k for k,v in locals().iteritems() if v == item][0] feas[retrieve_name(item)] = item return feas @@ -188,4 +188,3 @@ def retrieve_name(var): callers_local_vars = inspect.currentframe().f_back.f_locals.items() print([var_name for var_name, var_val in callers_local_vars if var_val is var]) return [var_name for var_name, var_val in callers_local_vars if var_val is var][0] - diff --git a/initializations.py b/initializations.py index cc2ec8f..eea6b72 100644 --- a/initializations.py +++ b/initializations.py @@ -1,6 +1,7 @@ import tensorflow as tf import numpy as np + def weight_variable_glorot(input_dim, output_dim, name=""): """Create a weight variable with Glorot & Bengio (AISTATS 2010) initialization. diff --git a/input_data.py b/input_data.py index 9782d31..e9a6fcf 100644 --- a/input_data.py +++ b/input_data.py @@ -11,12 +11,14 @@ def parse_index_file(filename): index.append(int(line.strip())) return index + def sample_mask(idx, l): """Create mask.""" mask = np.zeros(l) mask[idx] = 1 return np.array(mask, dtype=np.bool) + def load_data(dataset): # load the data: x, tx, allx, graph # x => 训练实例的特征向量，如scipy.sparse.csr.csr_matrix类的实例 @@ -42,9 +44,9 @@ def load_data(dataset): if dataset == 'citeseer': # Fix citeseer dataset (there are some isolated nodes in the graph) # Find isolated nodes, add them as zero-vecs into the right position、 - test_idx_range_full = range(min(test_idx_reorder), max(test_idx_reorder)+1) + test_idx_range_full = range(min(test_idx_reorder), max(test_idx_reorder) + 1) tx_extended = sp.lil_matrix((len(test_idx_range_full), x.shape[1])) - tx_extended[test_idx_range-min(test_idx_range), :] = tx + tx_extended[test_idx_range - min(test_idx_range), :] = tx tx = tx_extended ty_extended = np.zeros((len(test_idx_range_full), y.shape[1])) ty_extended[test_idx_range - min(test_idx_range), :] = ty @@ -72,7 +74,7 @@ def load_data(dataset): y_val[val_mask, :] = labels[val_mask, :] y_test[test_mask, :] = labels[test_mask, :] - return adj, features, y_test, tx, ty, test_mask, np.argmax(labels,1) + return adj, features, y_test, tx, ty, test_mask, np.argmax(labels, 1) def load_alldata(dataset_str): @@ -89,12 +91,12 @@ def load_alldata(dataset_str): if dataset_str == 'citeseer': # Fix citeseer dataset (there are some isolated nodes in the graph) # Find isolated nodes, add them as zero-vecs into the right position - test_idx_range_full = range(min(test_idx_reorder), max(test_idx_reorder)+1) + test_idx_range_full = range(min(test_idx_reorder), max(test_idx_reorder) + 1) tx_extended = sp.lil_matrix((len(test_idx_range_full), x.shape[1])) - tx_extended[test_idx_range-min(test_idx_range), :] = tx + tx_extended[test_idx_range - min(test_idx_range), :] = tx tx = tx_extended ty_extended = np.zeros((len(test_idx_range_full), y.shape[1])) - ty_extended[test_idx_range-min(test_idx_range), :] = ty + ty_extended[test_idx_range - min(test_idx_range), :] = ty ty = ty_extended features = sp.vstack((allx, tx)).tolil() @@ -106,7 +108,7 @@ def load_alldata(dataset_str): idx_test = test_idx_range.tolist() idx_train = range(len(y)) - idx_val = range(len(y), len(y)+500) + idx_val = range(len(y), len(y) + 500) train_mask = sample_mask(idx_train, labels.shape[0]) val_mask = sample_mask(idx_val, labels.shape[0]) diff --git a/layers.py b/layers.py index 8610eed..2f157af 100644 --- a/layers.py +++ b/layers.py @@ -32,7 +32,7 @@ def dropout_sparse(x, keep_prob, num_nonzero_elems): random_tensor += tf.random_uniform(noise_shape) dropout_mask = tf.cast(tf.floor(random_tensor), dtype=tf.bool) pre_out = tf.sparse_retain(x, dropout_mask) - return pre_out * (1./keep_prob) + return pre_out * (1. / keep_prob) class Layer(object): @@ -46,6 +46,7 @@ class Layer(object): (i.e. takes input, returns output) __call__(inputs): Wrapper for _call() """ + def __init__(self, **kwargs): allowed_kwargs = {'name', 'logging'} for kwarg in kwargs.keys(): @@ -71,6 +72,7 @@ class Layer(object): class GraphConvolution(Layer): """Basic graph convolution layer for undirected graph without edge labels.""" + def __init__(self, input_dim, output_dim, adj, dropout=0., act=tf.nn.relu, **kwargs): super(GraphConvolution, self).__init__(**kwargs) with tf.variable_scope(self.name + '_vars'): @@ -81,7 +83,7 @@ class GraphConvolution(Layer): def _call(self, inputs): x = inputs - x = tf.nn.dropout(x, 1-self.dropout) + x = tf.nn.dropout(x, 1 - self.dropout) x = tf.matmul(x, self.vars['weights']) x = tf.sparse_tensor_dense_matmul(self.adj, x) outputs = self.act(x) @@ -93,6 +95,7 @@ class GraphConvolutionSparse(Layer): Graph convolution layer for sparse inputs. 多了一个features_nonzero """ + def __init__(self, input_dim, output_dim, adj, features_nonzero, dropout=0., act=tf.nn.relu, **kwargs): super(GraphConvolutionSparse, self).__init__(**kwargs) with tf.variable_scope(self.name + '_vars'): @@ -105,7 +108,7 @@ class GraphConvolutionSparse(Layer): def _call(self, inputs): x = inputs - x = dropout_sparse(x, 1-self.dropout, self.features_nonzero) + x = dropout_sparse(x, 1 - self.dropout, self.features_nonzero) x = tf.sparse_tensor_dense_matmul(x, self.vars['weights']) x = tf.sparse_tensor_dense_matmul(self.adj, x) outputs = self.act(x) @@ -114,6 +117,7 @@ class GraphConvolutionSparse(Layer): class InnerProductDecoder(Layer): """Decoder model layer for link prediction.""" + def __init__(self, input_dim, dropout=0., act=tf.nn.sigmoid, **kwargs): super(InnerProductDecoder, self).__init__(**kwargs) self.dropout = dropout @@ -123,15 +127,17 @@ class InnerProductDecoder(Layer): """ 这个decoder部分实际上就只是input的转置再乘input """ - inputs = tf.nn.dropout(inputs, 1-self.dropout) + inputs = tf.nn.dropout(inputs, 1 - self.dropout) x = tf.transpose(inputs) x = tf.matmul(inputs, x) x = tf.reshape(x, [-1]) outputs = self.act(x) return outputs + class GraphConvolution_z2g(Layer): """Basic graph convolution layer for undirected graph without edge labels.""" + def __init__(self, input_dim, output_dim, adj, dropout=0., act=tf.nn.relu, **kwargs): super(GraphConvolution, self).__init__(**kwargs) with tf.variable_scope(self.name + '_vars'): @@ -142,16 +148,15 @@ class GraphConvolution_z2g(Layer): def _call(self, inputs): x = inputs - x = tf.nn.dropout(x, 1-self.dropout) + x = tf.nn.dropout(x, 1 - self.dropout) x = tf.matmul(x, self.vars['weights']) x = tf.sparse_tensor_dense_matmul(self.adj, x) outputs = self.act(x) return outputs - def _call(self, inputs): x = inputs - x = dropout_sparse(x, 1-self.dropout, self.features_nonzero) + x = dropout_sparse(x, 1 - self.dropout, self.features_nonzero) x = tf.sparse_tensor_dense_matmul(x, self.vars['weights']) x = tf.sparse_tensor_dense_matmul(self.adj, x) outputs = self.act(x) diff --git a/link_prediction.py b/link_prediction.py index 13fa156..84537d7 100644 --- a/link_prediction.py +++ b/link_prediction.py @@ -66,7 +66,8 @@ class Link_pred_Runner(): kde = KernelDensity(bandwidth=0.7).fit(featuresCompress) # construct model - d_real, discriminator, ae_model, model_z2g, D_Graph, GD_real = get_model(model_str, placeholders, feas['num_features'], feas['num_nodes'], feas['features_nonzero']) + d_real, discriminator, ae_model, model_z2g, D_Graph, GD_real = get_model(model_str, placeholders, feas['num_features'], feas['num_nodes'], + feas['features_nonzero']) # Optimizer opt = get_optimizer(model_str, ae_model, model_z2g, D_Graph, discriminator, placeholders, feas['pos_weight'], feas['norm'], d_real, feas['num_nodes'], GD_real) @@ -91,7 +92,8 @@ class Link_pred_Runner(): roc_curr, ap_curr, _ = lm_train.get_roc_score(emb, feas) val_roc_score.append(roc_curr) print("Epoch:", '%04d' % (epoch + 1), - "train_loss= {:.5f}, d_loss= {:.5f}, g_loss= {:.5f}, GD_loss= {:.5f}, GG_loss= {:.5f}".format(avg_cost[0], avg_cost[1], avg_cost[2], avg_cost[3], avg_cost[4]), "val_roc=", + "train_loss= {:.5f}, d_loss= {:.5f}, g_loss= {:.5f}, GD_loss= {:.5f}, GG_loss= {:.5f}".format(avg_cost[0], avg_cost[1], avg_cost[2], avg_cost[3], + avg_cost[4]), "val_roc=", "{:.5f}".format(val_roc_score[-1]), "val_ap=", "{:.5f}".format(ap_curr)) if (epoch + 1) % 10 == 0: diff --git a/metrics.py b/metrics.py index dd4563d..170f333 100644 --- a/metrics.py +++ b/metrics.py @@ -5,6 +5,7 @@ from sklearn import metrics from munkres import Munkres, print_matrix import numpy as np + class linkpred_metrics(): def __init__(self, edges_pos, edges_neg): self.edges_pos = edges_pos @@ -45,7 +46,6 @@ class clustering_metrics(): self.true_label = true_label self.pred_label = predict_label - def clusteringAcc(self): # best mapping between true_label and predict label l1 = list(set(self.true_label)) @@ -94,15 +94,16 @@ class clustering_metrics(): nmi = metrics.normalized_mutual_info_score(self.true_label, self.pred_label) adjscore = metrics.adjusted_rand_score(self.true_label, self.pred_label) acc, f1_macro, precision_macro, recall_macro, f1_micro, precision_micro, recall_micro = self.clusteringAcc() - - print('ACC=%f, f1_macro=%f, precision_macro=%f, recall_macro=%f, f1_micro=%f, precision_micro=%f, recall_micro=%f, NMI=%f, ADJ_RAND_SCORE=%f' % (acc, f1_macro, precision_macro, recall_macro, f1_micro, precision_micro, recall_micro, nmi, adjscore)) + + print('ACC=%f, f1_macro=%f, precision_macro=%f, recall_macro=%f, f1_micro=%f, precision_micro=%f, recall_micro=%f, NMI=%f, ADJ_RAND_SCORE=%f' % ( + acc, f1_macro, precision_macro, recall_macro, f1_micro, precision_micro, recall_micro, nmi, adjscore)) fh = open('recoder.txt', 'a') - fh.write('ACC=%f, f1_macro=%f, precision_macro=%f, recall_macro=%f, f1_micro=%f, precision_micro=%f, recall_micro=%f, NMI=%f, ADJ_RAND_SCORE=%f' % (acc, f1_macro, precision_macro, recall_macro, f1_micro, precision_micro, recall_micro, nmi, adjscore) ) + fh.write('ACC=%f, f1_macro=%f, precision_macro=%f, recall_macro=%f, f1_micro=%f, precision_micro=%f, recall_micro=%f, NMI=%f, ADJ_RAND_SCORE=%f' % ( + acc, f1_macro, precision_macro, recall_macro, f1_micro, precision_micro, recall_micro, nmi, adjscore)) fh.write('\r\n') fh.flush() fh.close() return acc, nmi, adjscore - diff --git a/model.py b/model.py index 05f0b73..a3d5016 100644 --- a/model.py +++ b/model.py @@ -4,6 +4,7 @@ import tensorflow as tf flags = tf.app.flags FLAGS = flags.FLAGS + class Model(object): def __init__(self, **kwargs): allowed_kwargs = {'name', 'logging'} @@ -56,43 +57,39 @@ class GCN(Model): self.adj = placeholders['adj'] self.dropout = placeholders['dropout'] - def construct(self, inputs = None, hidden = None, reuse = False): - if inputs == None : + def construct(self, inputs=None, hidden=None, reuse=False): + if inputs == None: inputs = self.inputs - + with tf.variable_scope('Encoder', reuse=reuse): self.hidden1 = GraphConvolutionSparse(input_dim=self.input_dim, output_dim=FLAGS.hidden1, adj=self.adj, - features_nonzero = self.features_nonzero, + features_nonzero=self.features_nonzero, act=tf.nn.relu, dropout=self.dropout, logging=self.logging, name='e_dense_1')(inputs) - - + self.noise = gaussian_noise_layer(self.hidden1, 0.1) if hidden == None: hidden = self.hidden1 self.embeddings = GraphConvolution(input_dim=FLAGS.hidden1, - output_dim=FLAGS.hidden2, - adj=self.adj, - act=lambda x: x, - dropout=self.dropout, - logging=self.logging, - name='e_dense_2')(hidden) - + output_dim=FLAGS.hidden2, + adj=self.adj, + act=lambda x: x, + dropout=self.dropout, + logging=self.logging, + name='e_dense_2')(hidden) self.z_mean = self.embeddings self.reconstructions = InnerProductDecoder(input_dim=FLAGS.hidden2, - act=lambda x: x, - logging=self.logging)(self.embeddings) + act=lambda x: x, + logging=self.logging)(self.embeddings) return self.z_mean, self.reconstructions - - class Generator_z2g(Model): def __init__(self, placeholders, num_features, features_nonzero, **kwargs): super(Generator_z2g, self).__init__(**kwargs) @@ -110,33 +107,28 @@ class Generator_z2g(Model): self.adj = placeholders['adj'] self.dropout = placeholders['dropout'] - - def construct(self, inputs = None, reuse = False): + def construct(self, inputs=None, reuse=False): if inputs == None: inputs = self.inputs with tf.variable_scope('Decoder', reuse=reuse): - self.hidden1 = GraphConvolution(input_dim=FLAGS.hidden2, - output_dim=FLAGS.hidden1, - adj=self.adj, - act=tf.nn.relu, - dropout=self.dropout, - logging=self.logging, - name='GG_dense_1')(inputs) - - + output_dim=FLAGS.hidden1, + adj=self.adj, + act=tf.nn.relu, + dropout=self.dropout, + logging=self.logging, + name='GG_dense_1')(inputs) self.embeddings = GraphConvolution(input_dim=FLAGS.hidden1, - output_dim=self.input_dim, - adj=self.adj, - act=lambda x: x, - dropout=self.dropout, - logging=self.logging, - name='GG_dense_2')(self.hidden1) - + output_dim=self.input_dim, + adj=self.adj, + act=lambda x: x, + dropout=self.dropout, + logging=self.logging, + name='GG_dense_2')(self.hidden1) self.z_mean = self.embeddings - return self.z_mean,self.hidden1 + return self.z_mean, self.hidden1 def dense(x, n1, n2, name): @@ -165,21 +157,23 @@ class D_graph(Model): self.act = tf.nn.relu self.num_features = num_features - def construct(self, inputs, reuse = False): + def construct(self, inputs, reuse=False): # input是一张Graph的adj，把每一列当成一个通道，所以input的通道数是num_nodes with tf.variable_scope('D_Graph'): if reuse: tf.get_variable_scope().reuse_variables() # np.random.seed(1) - #tf.set_random_seed(1) - dc_den1 = tf.nn.relu(dense(inputs, self.num_features, 512, name='GD_den1'))#(bs,num_nodes,512) - dc_den2 = tf.nn.relu(dense(dc_den1, 512, 128, name='GD_den2'))#(bs, num_nodes, 128) - output = dense(dc_den2, 128, 1, name='GD_output')#(bs,num_nodes,1) + # tf.set_random_seed(1) + dc_den1 = tf.nn.relu(dense(inputs, self.num_features, 512, name='GD_den1')) # (bs,num_nodes,512) + dc_den2 = tf.nn.relu(dense(dc_den1, 512, 128, name='GD_den2')) # (bs, num_nodes, 128) + output = dense(dc_den2, 128, 1, name='GD_output') # (bs,num_nodes,1) return output - + + def gaussian_noise_layer(input_layer, std): noise = tf.random_normal(shape=tf.shape(input_layer), mean=0.0, stddev=std, dtype=tf.float32) - return input_layer + noise + return input_layer + noise + class Discriminator(Model): def __init__(self, **kwargs): @@ -187,7 +181,7 @@ class Discriminator(Model): self.act = tf.nn.relu - def construct(self, inputs, reuse = False): + def construct(self, inputs, reuse=False): # with tf.name_scope('Discriminator'): with tf.variable_scope('Discriminator'): if reuse: @@ -197,4 +191,4 @@ class Discriminator(Model): dc_den1 = tf.nn.relu(dense(inputs, FLAGS.hidden2, FLAGS.hidden3, name='dc_den1')) dc_den2 = tf.nn.relu(dense(dc_den1, FLAGS.hidden3, FLAGS.hidden1, name='dc_den2')) output = dense(dc_den2, FLAGS.hidden1, 1, name='dc_output') - return output \ No newline at end of file + return output diff --git a/optimizer.py b/optimizer.py index 08a5757..10280b1 100644 --- a/optimizer.py +++ b/optimizer.py @@ -12,40 +12,37 @@ class OptimizerAE(object): self.real = d_real # Discrimminator Loss - #self.dc_loss_real = tf.reduce_mean( + # self.dc_loss_real = tf.reduce_mean( # tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.ones_like(self.real), logits=self.real,name='dclreal')) self.dc_loss_real = - tf.reduce_mean(self.real) - - #self.dc_loss_fake = tf.reduce_mean( + + # self.dc_loss_fake = tf.reduce_mean( # tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.zeros_like(d_fake), logits=d_fake,name='dcfake')) self.dc_loss_fake = tf.reduce_mean(d_fake) - GP_loss = tf.reduce_mean(tf.square(tf.sqrt(tf.reduce_mean(tf.square(gradient), axis = [0, 1])) - 1)) + GP_loss = tf.reduce_mean(tf.square(tf.sqrt(tf.reduce_mean(tf.square(gradient), axis=[0, 1])) - 1)) self.dc_loss = self.dc_loss_fake + self.dc_loss_real + GP_loss - #self.dc_loss = self.dc_loss_fake + self.dc_loss_real + # self.dc_loss = self.dc_loss_fake + self.dc_loss_real # Generator loss - #generator_loss = tf.reduce_mean( + # generator_loss = tf.reduce_mean( # tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.ones_like(d_fake), logits=d_fake, name='gl')) generator_loss = -self.dc_loss_fake - # pos_weight，允许人们通过向上或向下加权相对于负误差的正误差的成本来权衡召回率和精确度 self.cost = norm * tf.reduce_mean(tf.nn.weighted_cross_entropy_with_logits(logits=preds_sub, targets=labels_sub, pos_weight=pos_weight)) self.generator_loss = generator_loss + self.cost - all_variables = tf.trainable_variables() dc_var = [var for var in all_variables if 'dc_' in var.name] en_var = [var for var in all_variables if 'e_' in var.name] - with tf.variable_scope(tf.get_variable_scope()): self.discriminator_optimizer = tf.train.AdamOptimizer(learning_rate=FLAGS.discriminator_learning_rate, - beta1=0.9, name='adam1').minimize(self.dc_loss, var_list=dc_var) #minimize(dc_loss_real, var_list=dc_var) + beta1=0.9, name='adam1').minimize(self.dc_loss, + var_list=dc_var) # minimize(dc_loss_real, var_list=dc_var) self.generator_optimizer = tf.train.AdamOptimizer(learning_rate=FLAGS.discriminator_learning_rate, - beta1=0.9, name='adam2').minimize(self.generator_loss, var_list=en_var) - + beta1=0.9, name='adam2').minimize(self.generator_loss, var_list=en_var) # 值得注意的是，这个地方，除了对抗优化之外， # 还单纯用cost损失又优化了一遍， @@ -56,8 +53,7 @@ class OptimizerAE(object): class OptimizerCycle(object): - def __init__(self, preds, labels, pos_weight, norm, d_real, d_fake, GD_real, GD_fake, preds_z2g, labels_z2g, preds_cycle,labels_cycle,gradient, gradient_z): - + def __init__(self, preds, labels, pos_weight, norm, d_real, d_fake, GD_real, GD_fake, preds_z2g, labels_z2g, preds_cycle, labels_cycle, gradient, gradient_z): preds_sub = preds labels_sub = labels @@ -65,74 +61,71 @@ class OptimizerCycle(object): # Discrimminator Loss self.dc_loss_real = tf.reduce_mean( - tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.ones_like(self.real), logits=self.real,name='dclreal')) - #self.dc_loss_real = - tf.reduce_mean(self.real) + tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.ones_like(self.real), logits=self.real, name='dclreal')) + # self.dc_loss_real = - tf.reduce_mean(self.real) self.dc_loss_fake = tf.reduce_mean( - tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.zeros_like(d_fake), logits=d_fake,name='dcfake')) - #self.dc_loss_fake = tf.reduce_mean(d_fake) - #GP_loss = tf.reduce_mean(tf.square(tf.sqrt(tf.reduce_mean(tf.square(gradient), axis = [0, 1])) - 1)) - #GP_loss_z = tf.reduce_mean(tf.square(tf.sqrt(tf.reduce_mean(tf.square(gradient_z), axis = [0, 1])) - 1)) - #self.dc_loss = self.dc_loss_fake + self.dc_loss_real + 10.0 * GP_loss + tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.zeros_like(d_fake), logits=d_fake, name='dcfake')) + # self.dc_loss_fake = tf.reduce_mean(d_fake) + # GP_loss = tf.reduce_mean(tf.square(tf.sqrt(tf.reduce_mean(tf.square(gradient), axis = [0, 1])) - 1)) + # GP_loss_z = tf.reduce_mean(tf.square(tf.sqrt(tf.reduce_mean(tf.square(gradient_z), axis = [0, 1])) - 1)) + # self.dc_loss = self.dc_loss_fake + self.dc_loss_real + 10.0 * GP_loss self.GD_loss_real = tf.reduce_mean( - tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.ones_like(GD_real), logits=GD_real,name='GD_real')) - #self.GD_loss_real = - tf.reduce_mean(GD_real) + tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.ones_like(GD_real), logits=GD_real, name='GD_real')) + # self.GD_loss_real = - tf.reduce_mean(GD_real) self.GD_loss_fake = tf.reduce_mean( - tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.zeros_like(GD_fake), logits=GD_fake,name='GD_fake')) - #self.GD_loss_fake = tf.reduce_mean(GD_fake) - + tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.zeros_like(GD_fake), logits=GD_fake, name='GD_fake')) + # self.GD_loss_fake = tf.reduce_mean(GD_fake) + self.dc_loss = self.dc_loss_fake + self.dc_loss_real self.GD_loss = self.GD_loss_fake + self.GD_loss_real # Generator loss generator_loss = tf.reduce_mean( tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.ones_like(d_fake), logits=d_fake, name='gl')) - #generator_loss = -self.dc_loss_fake + # generator_loss = -self.dc_loss_fake generator_loss_z2g = tf.reduce_mean( tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.ones_like(GD_fake), logits=GD_fake, name='G_z2g')) - #generator_loss_z2g = -self.GD_loss_fake + # generator_loss_z2g = -self.GD_loss_fake # pos_weight，允许人们通过向上或向下加权相对于负误差的正误差的成本来权衡召回率和精确度 self.cost = norm * tf.reduce_mean(tf.nn.weighted_cross_entropy_with_logits(logits=preds_sub, targets=labels_sub, pos_weight=pos_weight)) - - + cost_cycle = norm * tf.reduce_mean(tf.square(preds_cycle - labels_cycle)) - cost_z2g = norm * tf.reduce_mean(tf.square(preds_z2g-labels_z2g)) - #with tf.device("/gpu:1"): - #self.cost = 0.00001*self.cost + cost_cycle #for citseer cluster + cost_z2g = norm * tf.reduce_mean(tf.square(preds_z2g - labels_z2g)) + # with tf.device("/gpu:1"): + # self.cost = 0.00001*self.cost + cost_cycle #for citseer cluster self.cost = self.cost + cost_cycle self.generator_loss = generator_loss + self.cost self.generator_loss_z2g = generator_loss_z2g - all_variables = tf.trainable_variables() dc_var = [var for var in all_variables if 'dc_' in var.name] en_var = [var for var in all_variables if 'e_' in var.name] GG_var = [var for var in all_variables if 'GG' in var.name] GD_var = [var for var in all_variables if 'GD' in var.name] - with tf.variable_scope(tf.get_variable_scope()): self.discriminator_optimizer = tf.train.AdamOptimizer(learning_rate=FLAGS.discriminator_learning_rate, - beta1=0.9, name='adam1').minimize(self.dc_loss, var_list=dc_var) #minimize(dc_loss_real, var_list=dc_var) + beta1=0.9, name='adam1').minimize(self.dc_loss, + var_list=dc_var) # minimize(dc_loss_real, var_list=dc_var) self.generator_optimizer = tf.train.AdamOptimizer(learning_rate=FLAGS.discriminator_learning_rate, - beta1=0.9, name='adam2').minimize(self.generator_loss, var_list=en_var) + beta1=0.9, name='adam2').minimize(self.generator_loss, var_list=en_var) self.discriminator_optimizer_z2g = tf.train.AdamOptimizer(learning_rate=FLAGS.discriminator_learning_rate, - beta1=0.9, name='adam1').minimize(self.GD_loss, var_list=GD_var) + beta1=0.9, name='adam1').minimize(self.GD_loss, var_list=GD_var) self.generator_optimizer_z2g = tf.train.AdamOptimizer(learning_rate=FLAGS.discriminator_learning_rate, - beta1=0.9, name='adam2').minimize(self.generator_loss_z2g, var_list=GG_var) - + beta1=0.9, name='adam2').minimize(self.generator_loss_z2g, var_list=GG_var) # 值得注意的是，这个地方，除了对抗优化之外， # 还单纯用cost损失又优化了一遍， # 待会儿看训练的时候注意看是在哪部分进行的这部分优化操作 self.optimizer = tf.train.AdamOptimizer(learning_rate=FLAGS.learning_rate) # Adam Optimizer self.opt_op = self.optimizer.minimize(self.cost) - #self.grads_vars = self.optimizer.compute_gradients(self.cost) - - #self.optimizer_z2g = tf.train.AdamOptimizer(learning_rate=FLAGS.learning_rate) # Adam Optimizer - #self.opt_op_z2g = self.optimizer.minimize(cost_z2g) - #self.grads_vars_z2g = self.optimizer.compute_gradients(cost_z2g) + # self.grads_vars = self.optimizer.compute_gradients(self.cost) + + # self.optimizer_z2g = tf.train.AdamOptimizer(learning_rate=FLAGS.learning_rate) # Adam Optimizer + # self.opt_op_z2g = self.optimizer.minimize(cost_z2g) + # self.grads_vars_z2g = self.optimizer.compute_gradients(cost_z2g) diff --git a/preprocessing.py b/preprocessing.py index fc8fdf5..d2ffb5e 100644 --- a/preprocessing.py +++ b/preprocessing.py @@ -3,7 +3,7 @@ import scipy.sparse as sp def sparse_to_tuple(sparse_mx): - #判断是否是coo_matrix，不是的话就转成coo_matrix + # 判断是否是coo_matrix，不是的话就转成coo_matrix if not sp.isspmatrix_coo(sparse_mx): sparse_mx = sparse_mx.tocoo() coords = np.vstack((sparse_mx.row, sparse_mx.col)).transpose() @@ -13,22 +13,22 @@ def sparse_to_tuple(sparse_mx): def preprocess_graph(adj): - # 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 + # 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 adj = sp.coo_matrix(adj) - adj_ = adj + sp.eye(adj.shape[0])#A* = A+I，即对邻接矩阵加入自连接 + adj_ = adj + sp.eye(adj.shape[0]) # A* = A+I，即对邻接矩阵加入自连接 - rowsum = np.array(adj_.sum(1))#对行求和，即得到节点的度 - degree_mat_inv_sqrt = sp.diags(np.power(rowsum, -0.5).flatten())#得到D的-1/2次方矩阵d - adj_normalized = adj_.dot(degree_mat_inv_sqrt).transpose().dot(degree_mat_inv_sqrt).tocoo()#这一步的实质是做归一化，即A* × d转置 × d + rowsum = np.array(adj_.sum(1)) # 对行求和，即得到节点的度 + degree_mat_inv_sqrt = sp.diags(np.power(rowsum, -0.5).flatten()) # 得到D的-1/2次方矩阵d + adj_normalized = adj_.dot(degree_mat_inv_sqrt).transpose().dot(degree_mat_inv_sqrt).tocoo() # 这一步的实质是做归一化，即A* × d转置 × d return sparse_to_tuple(adj_normalized) def construct_feed_dict(adj_normalized, adj, features, placeholders): # construct feed dictionary # .update()用法就是将()内的字段增加到dict当中 - feed_dict = dict()#创建一个空字典 + feed_dict = dict() # 创建一个空字典 feed_dict.update({placeholders['features']: features}) feed_dict.update({placeholders['adj']: adj_normalized}) feed_dict.update({placeholders['adj_orig']: adj}) @@ -44,7 +44,7 @@ def mask_test_edges(adj): # .diagonal()就是提取对角线元素 # Remove diagonal elements删除对角线元素 adj = adj - sp.dia_matrix((adj.diagonal()[np.newaxis, :], [0]), shape=adj.shape) - #把零元素都消除掉 + # 把零元素都消除掉 adj.eliminate_zeros() # Check that diag is zero: # np.diag(matrix)即提取matrix的对角线元素，todense() like toarray(),区别是一个是将存储方式由稀疏矩阵转成正常矩阵，另一个是转成array @@ -78,8 +78,8 @@ def mask_test_edges(adj): # 该函数的作用就是判断a元素是否存在于b集合中 rows_close = np.all(np.round(a - b[:, None], tol) == 0, axis=-1) return np.any(rows_close) - #return (np.all(np.any(rows_close, axis=-1), axis=-1) and - #np.all(np.any(rows_close, axis=0), axis=0)) + # return (np.all(np.any(rows_close, axis=-1), axis=-1) and + # np.all(np.any(rows_close, axis=0), axis=0)) # test_edges_false是去生成一些本来就不存在的edges test_edges_false = [] @@ -134,5 +134,3 @@ def mask_test_edges(adj): # NOTE: these edge lists only contain single direction of edge! return adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false - - diff --git a/run.py b/run.py index 229d4f6..783f75a 100644 --- a/run.py +++ b/run.py @@ -2,9 +2,9 @@ import settings from link_prediction import Link_pred_Runner -dataname = 'cora' # 'cora' or 'citeseer' or 'pubmed' -model = 'DBGAN' # 'arga_ae' or 'DBGAN' -task = 'link_prediction' +dataname = 'cora' # 'cora' or 'citeseer' or 'pubmed' +model = 'DBGAN' # 'arga_ae' or 'DBGAN' +task = 'link_prediction' settings = settings.get_settings(dataname, model, task) @@ -12,4 +12,3 @@ if task == 'link_prediction': runner = Link_pred_Runner(settings) runner.erun() - diff --git a/settings.py b/settings.py index aa19cb2..9581966 100644 --- a/settings.py +++ b/settings.py @@ -29,6 +29,7 @@ seed = 7 np.random.seed(seed) tf.set_random_seed(seed) + def get_settings(dataname, model, task): if dataname != 'citeseer' and dataname != 'cora' and dataname != 'pubmed': print('error: wrong data set name')