3

CTR预估之Wide&Deep系列模型:DeepFM/DCN

 11 months ago
source link: https://www.6aiq.com/article/1684850549719
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.

AIWeekly

via Mac OS
实时周报：https://github.com/cbamls/AI_Tutorial
  •  0 回帖  •  24 浏览  •  4 天前

CTR预估之Wide&Deep系列模型:DeepFM/DCN

image-3020e864e76243d2b96df4b8ad341c04.png-imageStyle
前言在CTR预估中， FM系列模型使用浅层网络（线性模型），让模型自己学习特征组合交互，为显式建模的方式；而DNN系列模型使用深层网络，隐式挖掘模型的高阶特征交互。本文继续介绍结合这两者优点的另外一个系列： Wide&Deep，即同时加入低阶特征组合交互的

CTR预估之Wide&Deep系列模型:DeepFM/DCN


report

Recommend

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK