/CTR_Algorithm

一些经典的CTR算法的复现; LR, FM, FFM, AFM, DeepFM, xDeepFM, PNN, DCN, DCNv2, DIFM, AutoInt, FiBiNet,AFN,ONN,DIN, DIEN ... (pytorch, tf2.0)

Primary LanguageJupyter Notebook

CTR Algorithm

根据论文, 博客, 知乎等方式学习一些CTR相关的算法
理解原理并自己动手来实现一遍
pytorch & tf2.0
保持一颗学徒的心!

Schedule

Model pytorch tensorflow2.0 paper
LR ✔️ ✔️ \
FM ✔️ ✔️ Factorization Machines, 2010.
FFM ✔️ ✔️ Field-aware Factorization Machines for CTR Prediction, 2015.
AFM ✔️ ✔️ Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks, 2017.
DeepFM ✔️ ✔️ DeepFM: A Factorization-Machine based Neural Network for CTR Prediction, 2017.
PNN ✔️ ✔️ Product-based Neural Networks for User Response Prediction, 2016.
XDeepFM ✔️ ✔️ xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems, 2018.
DCN ✔️ ✔️ Deep & Cross Network for Ad Click Predictions, 2017.
AutoInt ✔️ ✔️ AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks, 2018.
DIN ✔️ ✔️ Deep Interest Network for Click-Through Rate Prediction,2018
DIEN ✔️ ✔️ Deep Interest Evolution Network for Click-Through Rate Prediction,2019
FiBiNET ✔️ ✔️ FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction,2019
DCN-V2 ✔️ ✔️ Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems,2020
DIFM ✔️ ✔️ A Dual Input-aware Factorization Machine for CTR Prediction,2020
AFN ✔️ ✔️ Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions,2020
ONN ✔️ ✔️ Operation-aware Neural Networks for User Response Prediction,2019