-
Notifications
You must be signed in to change notification settings - Fork 650
/
MLP.py
178 lines (155 loc) · 7.57 KB
/
MLP.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
'''
Created on Aug 9, 2016
Keras Implementation of Multi-Layer Perceptron (GMF) recommender model in:
He Xiangnan et al. Neural Collaborative Filtering. In WWW 2017.
@author: Xiangnan He (xiangnanhe@gmail.com)
'''
import numpy as np
import theano
import theano.tensor as T
import keras
from keras import backend as K
from keras import initializations
from keras.regularizers import l2, activity_l2
from keras.models import Sequential, Graph, Model
from keras.layers.core import Dense, Lambda, Activation
from keras.layers import Embedding, Input, Dense, merge, Reshape, Merge, Flatten, Dropout
from keras.constraints import maxnorm
from keras.optimizers import Adagrad, Adam, SGD, RMSprop
from evaluate import evaluate_model
from Dataset import Dataset
from time import time
import sys
import argparse
import multiprocessing as mp
#################### Arguments ####################
def parse_args():
parser = argparse.ArgumentParser(description="Run MLP.")
parser.add_argument('--path', nargs='?', default='Data/',
help='Input data path.')
parser.add_argument('--dataset', nargs='?', default='ml-1m',
help='Choose a dataset.')
parser.add_argument('--epochs', type=int, default=100,
help='Number of epochs.')
parser.add_argument('--batch_size', type=int, default=256,
help='Batch size.')
parser.add_argument('--layers', nargs='?', default='[64,32,16,8]',
help="Size of each layer. Note that the first layer is the concatenation of user and item embeddings. So layers[0]/2 is the embedding size.")
parser.add_argument('--reg_layers', nargs='?', default='[0,0,0,0]',
help="Regularization for each layer")
parser.add_argument('--num_neg', type=int, default=4,
help='Number of negative instances to pair with a positive instance.')
parser.add_argument('--lr', type=float, default=0.001,
help='Learning rate.')
parser.add_argument('--learner', nargs='?', default='adam',
help='Specify an optimizer: adagrad, adam, rmsprop, sgd')
parser.add_argument('--verbose', type=int, default=1,
help='Show performance per X iterations')
parser.add_argument('--out', type=int, default=1,
help='Whether to save the trained model.')
return parser.parse_args()
def init_normal(shape, name=None):
return initializations.normal(shape, scale=0.01, name=name)
def get_model(num_users, num_items, layers = [20,10], reg_layers=[0,0]):
assert len(layers) == len(reg_layers)
num_layer = len(layers) #Number of layers in the MLP
# Input variables
user_input = Input(shape=(1,), dtype='int32', name = 'user_input')
item_input = Input(shape=(1,), dtype='int32', name = 'item_input')
MLP_Embedding_User = Embedding(input_dim = num_users, output_dim = layers[0]/2, name = 'user_embedding',
init = init_normal, W_regularizer = l2(reg_layers[0]), input_length=1)
MLP_Embedding_Item = Embedding(input_dim = num_items, output_dim = layers[0]/2, name = 'item_embedding',
init = init_normal, W_regularizer = l2(reg_layers[0]), input_length=1)
# Crucial to flatten an embedding vector!
user_latent = Flatten()(MLP_Embedding_User(user_input))
item_latent = Flatten()(MLP_Embedding_Item(item_input))
# The 0-th layer is the concatenation of embedding layers
vector = merge([user_latent, item_latent], mode = 'concat')
# MLP layers
for idx in xrange(1, num_layer):
layer = Dense(layers[idx], W_regularizer= l2(reg_layers[idx]), activation='relu', name = 'layer%d' %idx)
vector = layer(vector)
# Final prediction layer
prediction = Dense(1, activation='sigmoid', init='lecun_uniform', name = 'prediction')(vector)
model = Model(input=[user_input, item_input],
output=prediction)
return model
def get_train_instances(train, num_negatives):
user_input, item_input, labels = [],[],[]
num_users = train.shape[0]
for (u, i) in train.keys():
# positive instance
user_input.append(u)
item_input.append(i)
labels.append(1)
# negative instances
for t in xrange(num_negatives):
j = np.random.randint(num_items)
while train.has_key((u, j)):
j = np.random.randint(num_items)
user_input.append(u)
item_input.append(j)
labels.append(0)
return user_input, item_input, labels
if __name__ == '__main__':
args = parse_args()
path = args.path
dataset = args.dataset
layers = eval(args.layers)
reg_layers = eval(args.reg_layers)
num_negatives = args.num_neg
learner = args.learner
learning_rate = args.lr
batch_size = args.batch_size
epochs = args.epochs
verbose = args.verbose
topK = 10
evaluation_threads = 1 #mp.cpu_count()
print("MLP arguments: %s " %(args))
model_out_file = 'Pretrain/%s_MLP_%s_%d.h5' %(args.dataset, args.layers, time())
# Loading data
t1 = time()
dataset = Dataset(args.path + args.dataset)
train, testRatings, testNegatives = dataset.trainMatrix, dataset.testRatings, dataset.testNegatives
num_users, num_items = train.shape
print("Load data done [%.1f s]. #user=%d, #item=%d, #train=%d, #test=%d"
%(time()-t1, num_users, num_items, train.nnz, len(testRatings)))
# Build model
model = get_model(num_users, num_items, layers, reg_layers)
if learner.lower() == "adagrad":
model.compile(optimizer=Adagrad(lr=learning_rate), loss='binary_crossentropy')
elif learner.lower() == "rmsprop":
model.compile(optimizer=RMSprop(lr=learning_rate), loss='binary_crossentropy')
elif learner.lower() == "adam":
model.compile(optimizer=Adam(lr=learning_rate), loss='binary_crossentropy')
else:
model.compile(optimizer=SGD(lr=learning_rate), loss='binary_crossentropy')
# Check Init performance
t1 = time()
(hits, ndcgs) = evaluate_model(model, testRatings, testNegatives, topK, evaluation_threads)
hr, ndcg = np.array(hits).mean(), np.array(ndcgs).mean()
print('Init: HR = %.4f, NDCG = %.4f [%.1f]' %(hr, ndcg, time()-t1))
# Train model
best_hr, best_ndcg, best_iter = hr, ndcg, -1
for epoch in xrange(epochs):
t1 = time()
# Generate training instances
user_input, item_input, labels = get_train_instances(train, num_negatives)
# Training
hist = model.fit([np.array(user_input), np.array(item_input)], #input
np.array(labels), # labels
batch_size=batch_size, nb_epoch=1, verbose=0, shuffle=True)
t2 = time()
# Evaluation
if epoch %verbose == 0:
(hits, ndcgs) = evaluate_model(model, testRatings, testNegatives, topK, evaluation_threads)
hr, ndcg, loss = np.array(hits).mean(), np.array(ndcgs).mean(), hist.history['loss'][0]
print('Iteration %d [%.1f s]: HR = %.4f, NDCG = %.4f, loss = %.4f [%.1f s]'
% (epoch, t2-t1, hr, ndcg, loss, time()-t2))
if hr > best_hr:
best_hr, best_ndcg, best_iter = hr, ndcg, epoch
if args.out > 0:
model.save_weights(model_out_file, overwrite=True)
print("End. Best Iteration %d: HR = %.4f, NDCG = %.4f. " %(best_iter, best_hr, best_ndcg))
if args.out > 0:
print("The best MLP model is saved to %s" %(model_out_file))