Recommendation System using Graph Neural Networks

Setup

• Install Miniconda: https://docs.conda.io/en/latest/miniconda.html
• Open terminal: git clone [email protected]:mughees-asif/postgraduate-research-project.git
• Create a new environment [enter custom name instead of <ENV_NAME>] in the root directory of the project through an Anaconda terminal: conda create -n <ENV_NAME> python3 numpy tqdm
• Install PyTorch: https://pytorch.org/get-started/locally/
• Install Jupyter Notebook: conda install -c conda-forge notebook
• Open Jupyter environment through an Anaconda terminal: jupyter notebook
• Navigate to the root directory & open this notebook
• You should now be set-up to run this example
• Any problems: email me or ping me on LinkedIn

Overview

Note

• This is a postgraduate MSc. research project completed by Mughees Asif under the supervision of Dr Angadh Nanjangud at Queen Mary, University of London.
• The associated written evaluation can be found here.
• A presentation that complements this research can be sourced here.

Contributions

This project was developed with the help of the content researched by:

• Fan, W., Ma, Y., Li, Q., He, Y., Zhao, E., Tang, J. and Yin, D., 2019, May. Graph Neural Networks for Social Recommendation. In The World Wide Web Conference (pp. 417-426).