NeuRec
An open source neural recommender library
NeuRec is a comprehensive and flexible Python library for recommender systems that includes a large range of state-of-the-art neural recommender models. This library aims to solve general, social and sequential (i.e. next-item) recommendation tasks, using the Tensorflow library to provide 33 models out of the box. NeuRec is open source and available under the MIT license.
Features
Cross platform - run on any operating system with the available Docker images;
State-of-the-art - 33 neural recommender models available out of the box;
Flexible configuration - easily change the configuration settings to your exact requirements;
Easy expansion - quickly include models or datasets into NeuRec;
Fast execution - naturally support GPU, with a mutli-thread evaluator;
Detailed documentation - extensive documentation available as Jupyter notebooks in tutorial.ipynb.
Architecture
The architecture of NeuRec is shown in the diagram below:
Quick Start
Firstly, download this reposito