-
Notifications
You must be signed in to change notification settings - Fork 495
Wide & Deep Learning
潜心 edited this page Sep 14, 2020
·
2 revisions
Wide & Deep Learning for Recommender Systems
创新:Wide + Deep架构
原文笔记: https://mp.weixin.qq.com/s/LRghf8mj1hjUYri_m3AzBg

采用Criteo数据集进行测试。数据集的处理见utils文件,主要分为:
- 考虑到Criteo文件过大,因此可以通过
read_part和sample_sum读取部分数据进行测试; - 对缺失数据进行填充;
- 对密集数据
I1-I13进行归一化处理,对稀疏数据C1-C26进行重新编码LabelEncoder; - 整理得到
feature_columns; - 切分数据集,最后返回
feature_columns, (train_X, train_y), (test_X, test_y);
class WideDeep(tf.keras.Model):
def __init__(self, feature_columns, hidden_units, activation='relu',
dnn_dropout=0., embed_reg=1e-4):
"""
Wide&Deep
:param feature_columns: A list. dense_feature_columns + sparse_feature_columns
:param hidden_units: A list. Neural network hidden units.
:param activation: A string. Activation function of dnn.
:param dnn_dropout: A scalar. Dropout of dnn.
:param embed_reg: A scalar. The regularizer of embedding.
"""- file:Criteo文件;
- read_part:是否读取部分数据,
True; - sample_num:读取部分时,样本数量,
5000000; - test_size:测试集比例,
0.2; - embed_dim:Embedding维度,
8; - dnn_dropout:Dropout,
0.5; - hidden_unit:DNN的隐藏单元,
[256, 128, 64]; - learning_rate:学习率,
0.001; - batch_size:
4096; - epoch:
10;
采用Criteo数据集中前500w条数据,最终测试集的结果为:AUC:0.780731