没有合适的资源?快使用搜索试试~ 我知道了~
FiBiNet分享1
资源详情
资源评论
资源推荐
![](https://csdnimg.cn/release/download_crawler_static/86317376/bg1.jpg)
FiBiNET: Combining Feature Importance
and Bilinear feature Interaction for Click-
Through Rate Prediction
何荣炜
![](https://csdnimg.cn/release/download_crawler_static/86317376/bg2.jpg)
Abstract
• Problem : Many current works calculate the feature interactions in a
simple way such as Hadamard product and inner product and they
care less about the importance of features.
• FiBiNET
• the FiBiNET can dynamically learn the importance of features via the
Squeeze-Excitation network (SENET) mechanism
• it is able to effectively learn the feature interactions via bilinear function.
![](https://csdnimg.cn/release/download_crawler_static/86317376/bg3.jpg)
• As far as we know, different features have various importances for the
target task. For example, the feature occupation is more important
than the feature hobby when we predict a person’s income. Taking this
into consideration, we introduce a Squeeze-and-Excitation network
(SENET) to learn the weights of features dynamically.
• Besides, feature interaction is a key challenge in CTR prediction field
and many related works calculate the feature interactions in a simple
way such as Hadamard product and inner product.
• We propose a new fine-grained way in this paper to calculate the
feature interactions with the bilinear function.
![](https://csdnimg.cn/release/download_crawler_static/86317376/bg4.jpg)
RELATED WORK
• Factorization Machine and Its relevant variants (FM && FFM)
• Deep Learning based CTR Models
• FNN can capture only high-order feature interactions.
• expertise feature engineering is still needed on the input to the wide part of
WDL
• DeepFM replaces the wide part of WDL with FM and shares the feature
embedding between the FM and deep component.
• xDeepFM) also models the low-order and high-order feature interactions in an
explicit way by proposing a novel Compressed Interaction Network (CIN) part.
![](https://csdnimg.cn/release/download_crawler_static/86317376/bg5.jpg)
SENet Module
• The SENET is proved to be successful in image classification tasks
and won first place in the ILSVRC 2017 classification task.
• Sparse Input and Embedding Layer
• SENET Layer
剩余22页未读,继续阅读
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![docx](https://img-home.csdnimg.cn/images/20210720083331.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![docx](https://img-home.csdnimg.cn/images/20210720083331.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![avatar](https://profile-avatar.csdnimg.cn/297b47943c234e969abc4eb3d8d642e9_weixin_35786770.jpg!1)
熊比哒
- 粉丝: 30
- 资源: 292
上传资源 快速赚钱
我的内容管理 展开
我的资源 快来上传第一个资源
我的收益
登录查看自己的收益我的积分 登录查看自己的积分
我的C币 登录后查看C币余额
我的收藏
我的下载
下载帮助
![voice](https://csdnimg.cn/release/downloadcmsfe/public/img/voice.245cc511.png)
![center-task](https://csdnimg.cn/release/downloadcmsfe/public/img/center-task.c2eda91a.png)
安全验证
文档复制为VIP权益,开通VIP直接复制
![dialog-icon](https://csdnimg.cn/release/downloadcmsfe/public/img/green-success.6a4acb44.png)
评论0