Skip to content
/ Recommend-System-tf2.0 Public

原理解析及代码实战，推荐算法也可以很简单 🔥 想要系统的学习推荐算法的小伙伴，欢迎 Star 或者 Fork 到自己仓库进行学习🚀 有任何疑问欢迎提 Issues，也可加文末的联系方式向我询问！

github.com/jc-leehub/
650 stars 216 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

jc-LeeHub/Recommend-System-tf2.0

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

460 Commits
AFM
AFM
 
 
AutoInt
AutoInt
 
 
CCPM
CCPM
 
 
DCN
DCN
 
 
DIN
DIN
 
 
Data
Data
 
 
DeepCrossing
DeepCrossing
 
 
DeepFM
DeepFM
 
 
FFM
FFM
 
 
FGCNN
FGCNN
 
 
FM
FM
 
 
FNN
FNN
 
 
MMOE
MMOE
 
 
NFM
NFM
 
 
PNN
PNN
 
 
WideDeep
WideDeep
 
 
image
image
 
 
xDeepFM
xDeepFM
 
 
README.md
README.md
 
 
requirements.txt
requirements.txt
 
 

Repository files navigation

Recommend-System-TF2.0

此仓库用于记录在学习推荐系统过程中的知识产出，主要是对经典推荐算法的原理解析及代码实现。

算法包含但不仅限于下图中的算法，持续更新中...

Models List

Model Paper
FM [ICDM 2010] Fast Context-aware Recommendationswith Factorization Machines
CCPM [CIKM 2015] A Convolutional Click Prediction Model
FFM [RecSys 2016] Field-aware Factorization Machines for CTR Prediction
FNN [ECIR 2016] Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction
PNN [ICDM 2016] Product-based neural networks for user response prediction
Wide & Deep [DLRS 2016] Wide & Deep Learning for Recommender Systems
Deep Crossing [KDD 2016] Deep Crossing: Web-Scale Modeling withoutManually Crafted Combinatorial Features
DeepFM [IJCAI 2017] DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
Deep & Cross Network [ADKDD 2017] Deep & Cross Network for Ad Click Predictions
AFM [IJCAI 2017] Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks
NFM [SIGIR 2017] Neural Factorization Machines for Sparse Predictive Analytics
Piece-wise Linear Model [arxiv 2017] Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction
xDeepFM [KDD 2018] xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
DIN [KDD 2018] Deep Interest Network for Click-Through Rate Prediction
MMoE [KDD 2018] Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
FwFM [WWW 2018] Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising
AutoInt [CIKM 2019] AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
DIEN [AAAI 2019] Deep Interest Evolution Network for Click-Through Rate Prediction
ONN [arxiv 2019] Operation-aware Neural Networks for User Response Prediction
FGCNN [WWW 2019] Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction
DSIN [IJCAI 2019] Deep Session Interest Network for Click-Through Rate Prediction
FiBiNET [RecSys 2019] FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction
FLEN [arxiv 2019] FLEN: Leveraging Field for Scalable CTR Prediction
DCN V2 [arxiv 2020] DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems

Introduction

  • 原理结合代码食用更佳，掌握算法的最好方式就是用代码撸它

  • 原理解析可参考知乎专栏 推荐算法也可以很简单

  • 代码实践参考本仓库即可，每个模型都有对应README.md，对模型原理、代码结构、实验结果进行了介绍

Tips: 该仓库使用的代码均为TF2.0，如果你不熟悉该框架，可参考文档简单粗暴的Tensorflow2.0

Citation

  • 论文列表引用于浅梦，并作了相应补充. Weichen Shen.(2017). DeepCTR: Easy-to-use,Modular and Extendible package of deep-learning based CTR models. https://github.com/shenweichen/deepctr. 感谢整理！

About

About

原理解析及代码实战，推荐算法也可以很简单 🔥 想要系统的学习推荐算法的小伙伴，欢迎 Star 或者 Fork 到自己仓库进行学习🚀 有任何疑问欢迎提 Issues，也可加文末的联系方式向我询问！

github.com/jc-LeeHub/

Topics

afm tf2 fm ffm dcn deepfm fnn pnn autoint dien fgcnn ccpm dsin widedeep

Resources

Readme
Activity

Stars

650 stars

Watchers

7 watching

Forks

216 forks
Report repository

Releases 1

v1.0 Latest
Jan 7, 2021

Packages

No packages published

Languages