FFM论文解读以及在tensorflow2实现FFM代码
文章目录
前言
网上关于FFM的论文解读都是千篇一律，于是乎，精选网上各种对于FFM的分析制作一个思维导图，同时也借鉴网上其他人的tensorflow2的代码，实现了FFM的代码，相信作者，照着本篇文章推荐的内容保证你快速深入理解FFM算法思想。
一、论文解读以及论文分析
我将网上写的一些不错的回答制作成一个思维导图，里面有对FFM的分析，照着这个思路，能迅速的对论文思想有一个清晰地认识。链接如下
FFM论文学习流程
每一个模块都精选我自己认为写的最好的文章，分别点击对应的链接进行学习即可
看完论文之后，那么必须要手动实现一下代码，下面将介绍一下在tensorflow2中实现FFM的过程
; 二、tensorflow2实现FFM代码
1.导库
import tensorflow as tf
from tensorflow.keras import layers, optimizers
from tensorflow import keras
import numpy as np
import pandas as pd
2.数据预处理
2.数据预处理
def preprocess(x, y):
x = tf.cast(x, dtype=tf.float64)
y = tf.cast(y, dtype=tf.int64)
return x, y
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
data = load_breast_cancer()
x_train, x_test, y_train, y_test = train_test_split(data.data, data.target, test_size=0.2, random_state=111,
stratify=data.target)
print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)
train_db = tf.data.Dataset.from_tensor_slices((np.array(x_train), y_train))
train_db = train_db.shuffle(123).map(preprocess).batch(32)
print(train_db)
test_db = tf.data.Dataset.from_tensor_slices((np.array(x_test), y_test))
test_db = test_db.shuffle(123).map(preprocess).batch(32)
sample = next(iter(train_db))
print('sample:', sample[0].shape, sample[1].shape,
tf.reduce_min(sample[0]), tf.reduce_max(sample[0]))
3.建立模型并测试运行
class FFM(keras.Model):
def __init__(self, field_num, feature_field_dict, dim_num, k=8):
super(FFM, self).__init__()
self.field_num = field_num
self.k = k
self.feature_field_dict = feature_field_dict
self.dim_num = dim_num
def build(self, input_shape):
self.fc = tf.keras.layers.Dense(units=1,
bias_regularizer=tf.keras.regularizers.l2(0.01),
kernel_regularizer=tf.keras.regularizers.l1(0.02))
self.w = self.add_weight(shape=(input_shape[-1], self.field_num, self.k),
initializer='glorot_uniform',
trainable=True)
super(FFM, self).build(input_shape)
def call(self, x, training):
linear = self.fc(x)
temp = tf.cast(0, tf.float32)
temp = tf.expand_dims(temp, axis=0)
for j1 in range(self.dim_num):
for j2 in range(j1 + 1, self.dim_num):
f1 = self.feature_field_dict[j2]
f2 = self.feature_field_dict[j1]
# [, , k] * [, , k] = [, , k] -> [1, k]
ww = tf.expand_dims(tf.multiply(self.w[j1, f2, :], self.w[j2, f1, :]), axis=0)
# print(ww)
# [x, ] * [x, ] = [x, ] -> [x, 1]
xx = tf.expand_dims(tf.multiply(x[:, j1], x[:, j2]), axis=1)
# print(xx)
# [x, 1] @ [1, k] = [x, k]
store = tf.matmul(xx, ww)
# print(store)
# [x, k] -> [x]
temp += tf.reduce_mean(store, keepdims=True, axis=1)
print(temp)
out = layers.Add()([linear, temp])
return tf.sigmoid(out)
store = {}
for i in range(30):
store[i] = int(i / 15)
model = FFM(field_num=2, feature_field_dict=store, dim_num=30)
model.build((None, 30))
model.summary()
def main():
store = {}
for i in range(30):
store[i] = int(i / 15) # 实际要根据数据字段含义定义，这里只是做一个随意的分组
model = FFM(field_num=2, feature_field_dict=store, dim_num=30)
optimizer = optimizers.Adam(lr=1e-2)
for epoch in range(10):
for step, (x, y) in enumerate(train_db):
with tf.GradientTape() as tape:
logits = model(x, training=True)
loss = tf.reduce_mean(tf.losses.binary_crossentropy(y, logits))
loss_regularization = []
for i in model.trainable_variables:
loss_regularization.append(tf.nn.l2_loss(i))
loss_regularization = tf.reduce_sum(tf.stack(loss_regularization))
loss = 0.001 * loss_regularization + loss
grads = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(grads, model.trainable_variables))
print(epoch, step, 'loss:', float(loss))
total_num = 0
total_correct = 0
for x, y in test_db:
pred = model(x, training=False)
pred = tf.squeeze(pred)
pred = pred > 0.5
pred = tf.cast(pred, dtype=tf.int64)
correct = tf.cast(tf.equal(pred, y), tf.int64)
correct = tf.reduce_sum(correct)
total_num += x.shape[0]
total_correct += int(correct)
acc = total_correct / total_num
print(epoch, 'acc:', acc)
print("-" * 25)
if __name__ == '__main__':
main()
建议不懂得自己阅读调试代码，会更加深刻的理解论文思想
总结
本文就详细介绍了FFM论文的思想(其它人的解读）以及如何实现的过程，希望对读者朋友们有所帮助
Original: https://blog.csdn.net/weixin_43106956/article/details/121592873
Author: 向未来前行
Title: 全网最全——-FFM论文解读以及在tensorflow2实现FFM代码
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/520654/
转载文章受原作者版权保护。转载请注明原作者出处！