You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: models/rank/dmr/readme.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -32,8 +32,8 @@
32
32
-[FAQ](#FAQ)
33
33
34
34
## 模型简介
35
-
两个deep子网络获取user的两种抽象表达,得到U和target item的score,结合其他特征送入MLP计算ctr score。[Deep Match to Rank Model for Personalized Click-Through Rate Prediction](https://github.com/lvze92/DMR)文章通过 User-to-Item 子网络和 Item-to-Item 子网络来表征 U2I 相关性,再结合传统的rec model features,提升模型的表达能力。
两个deep子网络获取user的两种抽象表达,得到U和target item的score,结合其他特征送入MLP计算ctr score。[Deep Match to Rank Model for Personalized Click-Through Rate Prediction](https://github.com/lvze92/DMR/blob/master/%5BDMR%5D%20Deep%20Match%20to%20Rank%20Model%20for%20Personalized%20Click-Through%20Rate%20Prediction-AAAI20.pdf)文章通过 User-to-Item 子网络和 Item-to-Item 子网络来表征 U2I 相关性,再结合传统的rec model features,提升模型的表达能力。
论文[Deep Match to Rank Model for Personalized Click-Through Rate Prediction](https://github.com/lvze92/DMR)中的网络结构如图所示:
65
+
论文[Deep Match to Rank Model for Personalized Click-Through Rate Prediction](https://github.com/lvze92/DMR/blob/master/%5BDMR%5D%20Deep%20Match%20to%20Rank%20Model%20for%20Personalized%20Click-Through%20Rate%20Prediction-AAAI20.pdf)中的网络结构如图所示:
0 commit comments