Graph Neural Networks for Recommender Systems

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.

An Efficient and Effective Framework for Session-based Social Recommendation

SEFrame This repository contains the code for the paper "An Efficient and Effective Framework for Session-based Social Recommendation". Requirements P

Tianwen CHEN 23 Oct 26, 2022
Elliot is a comprehensive recommendation framework that analyzes the recommendation problem from the researcher's perspective.

Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluation

Information Systems Lab @ Polytechnic University of Bari 215 Nov 29, 2022
Bundle Graph Convolutional Network

Bundle Graph Convolutional Network This is our Pytorch implementation for the paper: Jianxin Chang, Chen Gao, Xiangnan He, Depeng Jin and Yong Li. Bun

55 Dec 25, 2022
Recommender systems are the systems that are designed to recommend things to the user based on many different factors

Recommender systems are the systems that are designed to recommend things to the user based on many different factors. The recommender system deals with a large volume of information present by filte

Happy N. Monday 3 Feb 15, 2022
This is our Tensorflow implementation for "Graph-based Embedding Smoothing for Sequential Recommendation" (GES) (TKDE, 2021).

Graph-based Embedding Smoothing (GES) This is our Tensorflow implementation for the paper: Tianyu Zhu, Leilei Sun, and Guoqing Chen. "Graph-based Embe

Tianyu Zhu 15 Nov 29, 2022
Jointly Learning Explainable Rules for Recommendation with Knowledge Graph

Jointly Learning Explainable Rules for Recommendation with Knowledge Graph

57 Nov 03, 2022
A tensorflow implementation of the RecoGCN model in a CIKM'19 paper, titled with "Relation-Aware Graph Convolutional Networks for Agent-Initiated Social E-Commerce Recommendation".

This repo contains a tensorflow implementation of RecoGCN and the experiment dataset Running the RecoGCN model python train.py Example training outp

xfl15 30 Nov 25, 2022
EXEMPLO DE SISTEMA ESPECIALISTA PARA RECOMENDAR SERIADOS EM PYTHON

exemplo-de-sistema-especialista EXEMPLO DE SISTEMA ESPECIALISTA PARA RECOMENDAR SERIADOS EM PYTHON Resumo O objetivo de auxiliar o usuário na escolha

Josue Lopes 3 Aug 31, 2021
Group-Buying Recommendation for Social E-Commerce

Group-Buying Recommendation for Social E-Commerce This is the official implementation of the paper Group-Buying Recommendation for Social E-Commerce (

Jun Zhang 37 Nov 28, 2022
Recommendation Systems for IBM Watson Studio platform

Recommendation-Systems-for-IBM-Watson-Studio-platform Project Overview In this project, I analyze the interactions that users have with articles on th

Milad Sadat-Mohammadi 1 Jan 21, 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.

Yu 1.4k Dec 27, 2022
Movie Recommender System

Movie-Recommender-System Movie-Recommender-System is a web application using which a user can select his/her watched movie from list and system will r

1 Jul 14, 2022
Cross-Domain Recommendation via Preference Propagation GraphNet.

PPGN Codes for CIKM 2019 paper Cross-Domain Recommendation via Preference Propagation GraphNet. Citation Please cite our paper if you find this code u

Information Retrieval Group, Wuhan University, China 20 Dec 15, 2022
Hierarchical Fashion Graph Network for Personalized Outfit Recommendation, SIGIR 2020

hierarchical_fashion_graph_network This is our Tensorflow implementation for the paper: Xingchen Li, Xiang Wang, Xiangnan He, Long Chen, Jun Xiao, and

LI Xingchen 70 Dec 05, 2022
Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks

Bi-TGCF Tensorflow Implementation of BiTGCF: Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks. in CIKM20

17 Nov 30, 2022
fastFM: A Library for Factorization Machines

Citing fastFM The library fastFM is an academic project. The time and resources spent developing fastFM are therefore justified by the number of citat

1k Dec 24, 2022
Code for my ORSUM, ACM RecSys 2020, HeroGRAPH: A Heterogeneous Graph Framework for Multi-Target Cross-Domain Recommendation

HeroGRAPH Code for my ORSUM @ RecSys 2020, HeroGRAPH: A Heterogeneous Graph Framework for Multi-Target Cross-Domain Recommendation Paper, workshop pro

Qiang Cui 9 Sep 14, 2022
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

Annoy Annoy (Approximate Nearest Neighbors Oh Yeah) is a C++ library with Python bindings to search for points in space that are close to a given quer

Spotify 10.6k Jan 01, 2023
Pytorch domain library for recommendation systems

TorchRec (Experimental Release) TorchRec is a PyTorch domain library built to provide common sparsity & parallelism primitives needed for large-scale

Meta Research 1.3k Jan 05, 2023
大规模推荐算法库,包含推荐系统经典及最新算法LR、Wide&Deep、DSSM、TDM、MIND、Word2Vec、DeepWalk、SSR、GRU4Rec、Youtube_dnn、NCF、GNN、FM、FFM、DeepFM、DCN、DIN、DIEN、DLRM、MMOE、PLE、ESMM、MAML、xDeepFM、DeepFEFM、NFM、AFM、RALM、Deep Crossing、PNN、BST、AutoInt、FGCNN、FLEN、ListWise等

(中文文档|简体中文|English) 什么是推荐系统? 推荐系统是在互联网信息爆炸式增长的时代背景下,帮助用户高效获得感兴趣信息的关键; 推荐系统也是帮助产品最大限度吸引用户、留存用户、增加用户粘性、提高用户转化率的银弹。 有无数优秀的产品依靠用户可感知的推荐系统建立了良好的口碑,也有无数的公司依

3.6k Dec 30, 2022