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".

Overview

This repo contains a tensorflow implementation of RecoGCN and the experiment dataset

Running the RecoGCN model

python train.py 

Example training output

Time elapsed = 6.89 mins, Training: loss = 389.51047, mrr = 0.63130, ndcg = 0.71369, hr1 = 0.50939, hr3 = 0.69945, hr5 = 0.78027, hr10 = 0.87522 | Val:loss = 2172.41870, mrr = 0.25467, ndcg = 0.40172, hr1 = 0.15110, hr3 = 0.25807, hr5 = 0.33136, hr10 = 0.45893

Example evaluation result

0	lr=0.0001,lamb=0.55,batch_size=400,numNegative=100,featEmbedDim=64,idenEmbedDim=64,outputDim=128,pathNum=7	Test loss:2033.5934; Test mrr:0.25339168; Test ndcg:0.3976466; Test hr1:0.14939758; Test hr3:0.2633283; Test hr5:0.34176204; Test hr10:0.46430722

These variant models below had been supported:

  • ReGCN
  • ReGCN_{MP}
  • RecoGCN

Dependencies (other versions may also work):

  • python == 3.6
  • tensorflow == 1.13.1
  • numpy == 1.16.3
  • h5py == 2.9.0
  • GPUtil ==1.4.0
  • setproctitle == 1.1.10

Dataset

You can download the experiment data from Here. An example loading code is provided as follow.

adj = {0:{}, 1:{}, 2:{}, 3:{}}
with h5py.File(dataset, 'r') as f:
	adj[0][1] = f['adj01'][:]
	adj[1][0] = f['adj10'][:]
	adj[0][2] = f['adj02'][:]
	adj[2][0] = f['adj20'][:]
	adj[0][3] = f['adj03'][:]
	adj[3][0] = f['adj30'][:]

	train_sample = f['train_sample'][:]
	val_sample = f['val_sample'][:]
	test_sample = f['test_sample'][:]
		
	item_freq = f['item_freq'][:]
	user_feature = f['user_feature'][:]
	agent_feature = f['agent_feature'][:]
	item_feature = f['item_feature'][:]

	userCnt = f['userCnt'][()]
	agentCnt = f['agentCnt'][()]
	itemCnt = f['itemCnt'][()]

The data structure is explained as follow.

adj[x][y] denotes the adjancy relationship from x to y. Here, 0 stands for user, 1 is selling agent, 2 and 3 are two kinds of items. The shape of adj[x][y] is [Num_of_node_x ,maximum_link]. Each line stores the node ids of type y who are linked with node x. Note that maximum_link should be the same for each of these relations.

train_sample, val_sample, test_sample are triplet of [user, selling_agent, item] pairs. Each type of node is encoded from 0.

item_freq is [item_id, item_frequency] matrix denotes the occur frequency of each item in train set.

user_feature, agent_feature, item_feature are three featrue matrix of shape [node_num, feature_num]. Here features for each node are multi-hot encoded, and different type of node can have different feature numbers.

Citation

If you use our code or dataset in your research, please cite:

@inproceedings{xu2019relation,
  title={Relation-aware graph convolutional networks for agent-initiated social e-commerce recommendation},
  author={Xu, Fengli and Lian, Jianxun and Han, Zhenyu and Li, Yong and Xu, Yujian and Xie, Xing},
  booktitle={Proceedings of the 28th ACM International Conference on Information and Knowledge Management},
  pages={529--538},
  year={2019}
}
Owner
xfl15
xfl15
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
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

Jonathan Soma 87 Nov 29, 2022
Books Recommendation With Python

Books-Recommendation Business Problem During the last few decades, with the rise

Çağrı Karadeniz 7 Mar 12, 2022
It is a movie recommender web application which is developed using the Python.

Movie Recommendation 🍿 System Watch Tutorial for this project Source IMDB Movie 5000 Dataset Inspired from this original repository. Features Simple

Kushal Bhavsar 10 Dec 26, 2022
The official implementation of "DGCN: Diversified Recommendation with Graph Convolutional Networks" (WWW '21)

DGCN This is the official implementation of our WWW'21 paper: Yu Zheng, Chen Gao, Liang Chen, Depeng Jin, Yong Li, DGCN: Diversified Recommendation wi

FIB LAB, Tsinghua University 37 Dec 18, 2022
RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems

RecSim NG, a probabilistic platform for multi-agent recommender systems simulation. RecSimNG is a scalable, modular, differentiable simulator implemented in Edward2 and TensorFlow. It offers: a power

Google Research 110 Dec 16, 2022
Graph Neural Network based Social Recommendation Model. SIGIR2019.

Basic Information: This code is released for the papers: Le Wu, Peijie Sun, Yanjie Fu, Richang Hong, Xiting Wang and Meng Wang. A Neural Influence Dif

PeijieSun 144 Dec 29, 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
Detecting Beneficial Feature Interactions for Recommender Systems, AAAI 2021

Detecting Beneficial Feature Interactions for Recommender Systems (L0-SIGN) This is our implementation for the paper: Su, Y., Zhang, R., Erfani, S., &

26 Nov 22, 2022
Mutual Fund Recommender System. Tailor for fund transactions.

Explainable Mutual Fund Recommendation Data Please see 'DATA_DESCRIPTION.md' for mode detail. Recommender System Methods Baseline Collabarative Fiilte

JHJu 2 May 19, 2022
Deep recommender models using PyTorch.

Spotlight uses PyTorch to build both deep and shallow recommender models. By providing both a slew of building blocks for loss functions (various poin

Maciej Kula 2.8k Dec 29, 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
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
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
Code for ICML2019 Paper "Compositional Invariance Constraints for Graph Embeddings"

Dependencies NOTE: This code has been updated, if you were using this repo earlier and experienced issues that was due to an outaded codebase. Please

Avishek (Joey) Bose 43 Nov 25, 2022
A Library for Field-aware Factorization Machines

Table of Contents ================= - What is LIBFFM - Overfitting and Early Stopping - Installation - Data Format - Command Line Usage - Examples -

1.6k Dec 05, 2022
Real time recommendation playground

concierge A continuous learning collaborative filter1 deployed with a light web server2. Distributed updates are live (real time pubsub + delta traini

Mark Essel 16 Nov 07, 2022
Handling Information Loss of Graph Neural Networks for Session-based Recommendation

LESSR A PyTorch implementation of LESSR (Lossless Edge-order preserving aggregation and Shortcut graph attention for Session-based Recommendation) fro

Tianwen CHEN 62 Dec 03, 2022
6002project-rl - An implemention of offline RL on recommender system

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

Tzay Lee 3 May 24, 2022
Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

DANSER-WWW-19 This repository holds the codes for Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recom

Qitian Wu 78 Dec 10, 2022