gnikh / Co-Action-Network

Implementation of CAN: Revisiting Feature Co-Action for Click-Through RatePrediction

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Co-Action Network

Implementation of paper "CAN: Revisiting Feature Co-Action for Click Through Rate Prediction".

paper: arxiv (to be released)

Installation

dependences:

tensorflow:1.4.1

python: 2.7

higher version of tensorflow and python3 will be supported soon!

Getting Started

training:

CUDA_VISIBLE_DEVICES=0 python script/train.py train {model}

model: CAN,Cartesion,PNN, etc. (check the train.py)

Citation

Contact

License

About

Implementation of CAN: Revisiting Feature Co-Action for Click-Through RatePrediction


Languages

Language:Python 99.8%Language:Shell 0.2%