Skip to content

LR model solved by ftrl and sgd parallel on parameter server(ps-lite). FM、FFM model in the future

Notifications You must be signed in to change notification settings

lambdaji/Field-aware-Factorization-Machine-ps

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

90 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

  1. Introduction

    Distributed LR With Parameter Server

  2. Install

    step 1. in the fold of logistic-regression-ftrl-ps

     cd ps-lite
    
     cp third_party/* .
    
     make
    

    step 2.

     cd dmlc-core
    
     make
    

    step 3.

     cd Field-aware-Factorization-Machine-ps
    
     make clean && make
    
  3. todo:

    1. FM model

    2. FFM model

    3. Learning hyper parameters of normazation automatically

    4. opt algo for more sparse model

  4. Contact:

    [email protected]

  5. References:

    [1] Ad Click Prediction: a View from the Trenches:http:https://dl.acm.org/citation.cfm?id=2488200

About

LR model solved by ftrl and sgd parallel on parameter server(ps-lite). FM、FFM model in the future

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages

  • C++ 71.0%
  • Python 11.8%
  • Java 4.7%
  • C 3.7%
  • CMake 3.5%
  • Makefile 3.1%
  • Other 2.2%