/CF-NADE

A implementation of CF-NADE. Yin Zheng, et. al. "A Neural Autoregressive Approach to Collaborative Filtering", accepted by ICML 2016.

Primary LanguagePython

Code for "A Neural Autoregressive Approach to Collaborative Filtering", ICML 2016

Dependency:

You need to install:
Theano: http://deeplearning.net/software/theano/
blocks: http://blocks.readthedocs.io/en/latest/bricks_overview.html
		version 0.1.1 is requred


In this code, you can use the code in "datasets" to generate a hdf5 dataset to feed CF-NADE. 
Then you can run "learner_ordinalcost_directly_itembased_newsoftmax_timing.py" to train and 
test CF-NADE.

And example to run the code is:

MovieLens1M=/Users/yin.zheng/ml_datasets/MovieLens1M-shuffle-itembased-0 python learner_ordinalcost_directly_itembased_newsoftmax_timing.py 512 10 60 0.001 0.1 0.001 1e-8 500 tanh 0 0.02 Adam 0 1 0.995 /tmp/cfnade