Graph Neural Networks for Recommender Systems

Last update: Jan 4, 2023

Related tags

Overview

GNN-RecSys

This project was presented in a 40min talk + Q&A available on Youtube and in a Medium blog post

Graph Neural Networks for Recommender Systems
This repository contains code to train and test GNN models for recommendation, mainly using the Deep Graph Library (DGL).

What kind of recommendation?
For example, an organisation might want to recommend items of interest to all users of its ecommerce platforms.

How can this repository can be used?
This repository is aimed at helping users that wish to experiment with GNNs for recommendation, by giving a real example of code to build a GNN model, train it and serve recommendations.

No training data, experiments logs, or trained model are available in this repository.

What should the data look like?
To run the code, users need multiple data sources, notably interaction data between user and items and features of users and items.

The interaction data sources should be adjacency lists. Here is an example:

customer_id	item_id	timestamp	click	purchase
imbvblxwvtiywunh	3384934262863770	2018-01-01	0	1
nzhrkquelkgflone	8321263216904593	2018-01-01	1	0
...	...	...	...	...
cgatomzvjiizvctb	2756920171861146	2019-12-31	1	0
cnspkotxubxnxtzk	5150255386059428	2019-12-31	0	1

The feature data should have node identifier and node features:

customer_id	is_male	is_female
imbvblxwvtiywunh	0	1
nzhrkquelkgflone	1	0
...	...	...
cgatomzvjiizvctb	0	1
cnspkotxubxnxtzk	0	1

Run the code

There are 3 different usages of the code: hyperparametrization, training and inference. Examples of how to run the code are presented in UseCases.ipynb.

All 3 usages require specific files to be available. Please refer to the docstring to see which files are required.

Hyperparametrization

Hyperparametrization is done using the main.py file. Going through the space of hyperparameters, the loop builds a GNN model, trains it on a sample of training data, and computes its performance metrics. The metrics are reported in a result txt file, and the best model's parameters are saved in the models directory. Plots of the training experiments are saved in the plots directory. Examples of recommendations are saved in the outputs directory.

python main.py --from_beginning -v --visualization --check_embedding --remove 0.85 --num_epochs 100 --patience 5 --edge_batch_size 1024 --item_id_type 'ITEM IDENTIFIER' --duplicates 'keep_all'

Refer to docstrings of main.py for details on parameters.

Training

When the hyperparameters are selected, it is possible to train the chosen GNN model on the available data. This process saves the trained model in the models directory. Plots, training logs, and examples of recommendations are saved.

python main_train.py --fixed_params_path test/fixed_params_example.pkl --params_path test/params_example.pkl --visualization --check_embedding --remove .85 --edge_batch_size 512

Refer to docstrings of main_train.py for details on parameters.

Inference

With a trained model, it is possible to generate recommendations for all users or specific users. Examples of recommendations are printed.

python main_inference.py --params_path test/final_params_example.pkl --user_ids 123456 \
--user_ids 654321 --user_ids 999 \
--trained_model_path test/final_model_trained_example.pth --k 10 --remove .99

Refer to docstrings of main_inference.py for details on parameters.

6002project-rl - An implemention of offline RL on recommender system

An implemention of offline RL on recommender system @author: misajie @update: 20

3 May 24, 2022

Plex-recommender - Get movie recommendations based on your current PleX library

plex-recommender Description: Get movie/tv recommendations based on your current

5 Jul 19, 2022

Persine is an automated tool to study and reverse-engineer algorithmic recommendation systems.

Persine, the Persona Engine Persine is an automated tool to study and reverse-engineer algorithmic recommendation systems. It has a simple interface a

87 Nov 29, 2022

Graph Neural Networks for Recommender Systems

This repository contains code to train and test GNN models for recommendation, mainly using the Deep Graph Library (DGL).

217 Jan 4, 2023

A Comparative Framework for Multimodal Recommender Systems

Cornac Cornac is a comparative framework for multimodal recommender systems. It focuses on making it convenient to work with models leveraging auxilia

671 Jan 3, 2023

A Python scikit for building and analyzing recommender systems

Overview Surprise is a Python scikit for building and analyzing recommender systems that deal with explicit rating data. Surprise was designed with th

5.7k Jan 1, 2023

A library for preparing, training, and evaluating scalable deep learning hybrid recommender systems using PyTorch.

collie_recs Collie is a library for preparing, training, and evaluating implicit deep learning hybrid recommender systems, named after the Border Coll

97 Jan 3, 2023

NVIDIA Merlin is an open source library designed to accelerate recommender systems on NVIDIA’s GPUs.

NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.

420 Jan 4, 2023

Collaborative variational bandwidth auto-encoder (VBAE) for recommender systems.

Collaborative Variational Bandwidth Auto-encoder The codes are associated with the following paper: Collaborative Variational Bandwidth Auto-encoder f

14 Dec 11, 2022

Open-sourcing the Slates Dataset for recommender systems research

FINN.no Recommender Systems Slate Dataset This repository accompany the paper "Dynamic Slate Recommendation with Gated Recurrent Units and Thompson Sa

48 Nov 28, 2022

QRec: A Python Framework for quick implementation of recommender systems (TensorFlow Based)

QRec is a Python framework for recommender systems (Supported by Python 3.7.4 and Tensorflow 1.14+) in which a number of influential and newly state-of-the-art recommendation models are implemented. QRec has a lightweight architecture and provides user-friendly interfaces. It can facilitate model implementation and evaluation.

1.4k Dec 27, 2022

NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.

NVIDIA Merlin NVIDIA Merlin is an open source library designed to accelerate recommender systems on NVIDIA’s GPUs. It enables data scientists, machine

419 Jan 3, 2023

A library for preparing, training, and evaluating scalable deep learning hybrid recommender systems using PyTorch.

collie Collie is a library for preparing, training, and evaluating implicit deep learning hybrid recommender systems, named after the Border Collie do

96 Dec 29, 2022

An efficient PyTorch implementation of the evaluation metrics in recommender systems.

recsys_metrics An efficient PyTorch implementation of the evaluation metrics in recommender systems. Overview • Installation • How to use • Benchmark

12 Dec 2, 2022

E-Commerce recommender demo with real-time data and a graph database

🔍 E-Commerce recommender demo 🔍 This is a simple stream setup that uses Memgraph to ingest real-time data from a simulated online store. Data is str

3 Feb 23, 2022

We have implemented shaDow-GNN as a general and powerful pipeline for graph representation learning. For more details, please find our paper titled Deep Graph Neural Networks with Shallow Subgraph Samplers, available on arXiv (https//arxiv.org/abs/2012.01380).

Deep GNN, Shallow Sampling Hanqing Zeng, Muhan Zhang, Yinglong Xia, Ajitesh Srivastava, Andrey Malevich, Rajgopal Kannan, Viktor Prasanna, Long Jin, R

117 Dec 20, 2022

A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.

python_graphs This package is for computing graph representations of Python programs for machine learning applications. It includes the following modu

258 Dec 29, 2022

The source code of the paper "Understanding Graph Neural Networks from Graph Signal Denoising Perspectives"

GSDN-F and GSDN-EF This repository provides a reference implementation of GSDN-F and GSDN-EF as described in the paper "Understanding Graph Neural Net

18 Nov 14, 2022

Some tentative models that incorporate label propagation to graph neural networks for graph representation learning in nodes, links or graphs.

1 Nov 18, 2021

Comments

Error: Got unexpected extra argument (IDENTIFIER')

I found this error when I tried to compile the first usage "Hyperparametrization", below is the error message, is there any way can fix that error, thank you.

Error: Got unexpected extra argument (IDENTIFIER')

opened by hhrr0612 0

Graph Neural Networks for Recommender Systems

Related tags

Overview

GNN-RecSys

Run the code

Hyperparametrization

Training

Inference

You might also like...

6002project-rl - An implemention of offline RL on recommender system

Plex-recommender - Get movie recommendations based on your current PleX library

Persine is an automated tool to study and reverse-engineer algorithmic recommendation systems.

Graph Neural Networks for Recommender Systems

A Comparative Framework for Multimodal Recommender Systems

A Python scikit for building and analyzing recommender systems

A library for preparing, training, and evaluating scalable deep learning hybrid recommender systems using PyTorch.

NVIDIA Merlin is an open source library designed to accelerate recommender systems on NVIDIA’s GPUs.

Collaborative variational bandwidth auto-encoder (VBAE) for recommender systems.

Open-sourcing the Slates Dataset for recommender systems research

QRec: A Python Framework for quick implementation of recommender systems (TensorFlow Based)

NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.

A library for preparing, training, and evaluating scalable deep learning hybrid recommender systems using PyTorch.

An efficient PyTorch implementation of the evaluation metrics in recommender systems.

E-Commerce recommender demo with real-time data and a graph database

We have implemented shaDow-GNN as a general and powerful pipeline for graph representation learning. For more details, please find our paper titled Deep Graph Neural Networks with Shallow Subgraph Samplers, available on arXiv (https//arxiv.org/abs/2012.01380).

A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.

The source code of the paper "Understanding Graph Neural Networks from Graph Signal Denoising Perspectives"

Some tentative models that incorporate label propagation to graph neural networks for graph representation learning in nodes, links or graphs.

Comments

Error: Got unexpected extra argument (IDENTIFIER')

Owner

NVIDIA Merlin is an open source library designed to accelerate recommender systems on NVIDIA’s GPUs.

Collaborative variational bandwidth auto-encoder (VBAE) for recommender systems.

QRec: A Python Framework for quick implementation of recommender systems (TensorFlow Based)

E-Commerce recommender demo with real-time data and a graph database

Deep recommender models using PyTorch.

Recommender System Papers

RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems

Movie Recommender System

Mutual Fund Recommender System. Tailor for fund transactions.

Movies/TV Recommender