Skip to content
/ TF Public

Python implementation of N-dimensional Tensor Factorization

Notifications You must be signed in to change notification settings

VincentLiu3/TF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Tensor Factorization

This is a python implementation of tensor factorization (tucker decomposition) using SGD and ALS.

Input Data Format

Each row presents one rating infomation. The last column is rating value (float) and the rest are features (integer).

Feat1,Feat2,Feat3,Rating
    0,    3,    1,    2
    1,    2,    2,    4

Quick Start

$ python TF.py --train data/ml-1m/user_train.txt --test data/ml-1m/user_test.txt --reg 0.1 --regS 0.1 --lr 0.001 --lrS 0.001

You can type python TF.py --help for more details about the parameters. It is recommended to start from a small learning rate (especially for lrS).

Reference

* Karatzoglou, Alexandros, et al. Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering. Proceedings of the fourth ACM conference on Recommender systems. ACM, 2010.

About

Python implementation of N-dimensional Tensor Factorization

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages