The implementation of our CIKM 2021 paper titled as: "Cross-Market Product Recommendation"

Related tags

Deep LearningFOREC
Overview

FOREC: A Cross-Market Recommendation System

This repository provides the implementation of our CIKM 2021 paper titled as "Cross-Market Product Recommendation". Please consider citing our paper if you find the code and XMarket dataset useful in your research.

The general schema of our FOREC recommendation system is shown below. For a pair of markets, the middle part shows the market-agnostic model that we pre-train, and then fork and fine-tune for each market shown in the left and right. Note that FOREC is capable of working with any desired number of target markets. However, for simplicity, we only experiment with pairs of markets for the experiments. For further details, please refer to our paper.

Requirements:

We use conda for our experimentations. Please refer to the requirements.txt for the list of libraries we use for our implementation. After setting up your environment, you can simply run this command pip install -r requirements.txt.

DATA

The DATA folder in this repository contains the cleaned and proccessed data that we use for our experiments. Please note that we made a few changes with releasing the data, and you might see slightly different numbers compared to the reported numbers in the paper.

If you wish to repeat the process on other categories of data or change the data preprocessing steps, prepare_data.ipynb provides the code for downloading and preprocessing data. Please refer to that jupyter notebook for further details. Don't hesitate to contact us in case of any problem.

Train the baseline and FOREC models (with Evaluations):

We provide three training scripts, for training baselines (single market, GMF, MLP, NMF++ and MAML) as well as FOREC model. Here are the list of models that for training and evaluating with the scripts provided:

  • train_base.py for GMF, MLP, NMF and their ++ versions as cross-market models
  • train_maml.py for training our MAML baseline
  • train_forec.py for trainig our proposed FOREC model

Note that since MAML and FOREC works on NMF architecture, you need to have same setting NMF++ model trained before proceeding with the MAML and FOREC training scripts. In addition, NMF requires that GMF and MLP models are trained, as it combines these two models into the architecture with some additional layers. See the middle part of the FOREC schema above.

In order to faciliate this, we provide a jupyter notebook (train_all.ipynb) that generates correct commands for all these trainings on any desired target market and augmenting source market pairs. Please follow the notebook for the training. For our trainings, we use slurm job management system on our server. However, you can still use/change the bash script generating part in the notebook to fit your own setup. These scripts are written into scripts folder created by the notebook. The logging of the training is alos in this directory under log sub-directory.

Note that for each of these, the train script evaluates on validation and test data (leave-one-out procedure for splitting---see data.py). The detailed evaluation results are dumped into EVAL folder as json files. Our trained checkpoints and an aggregator of evaluation json files will be provided shortly.

Citation

If you use this dataset, please refer to our CIKM’21 paper:

@inproceedings{bonab2021crossmarket,
    author = {Bonab, Hamed and Aliannejadi, Mohammad and Vardasbi, Ali and Kanoulas, Evangelos and Allan, James},
    booktitle = {Proceedings of the 30th ACM International Conference on Information \& Knowledge Management},
    publisher = {ACM},
    title = {Cross-Market Product Recommendation},
    year = {2021}}

Please feel free to either open an issue or contacting me at bonab [AT] cs.umass.edu

Owner
Hamed Bonab
PhD Candidate at UMass Amherst
Hamed Bonab
DI-HPC is an acceleration operator component for general algorithm modules in reinforcement learning algorithms

DI-HPC: Decision Intelligence - High Performance Computation DI-HPC is an acceleration operator component for general algorithm modules in reinforceme

OpenDILab 185 Dec 29, 2022
Simple improvement of VQVAE that allow to generate x2 sized images compared to baseline

vqvae_dwt_distiller.pytorch Simple improvement of VQVAE that allow to generate x2 sized images compared to baseline. It allows to generate 512x512 ima

Sergei Belousov 25 Jul 19, 2022
GB-CosFace: Rethinking Softmax-based Face Recognition from the Perspective of Open Set Classification

GB-CosFace: Rethinking Softmax-based Face Recognition from the Perspective of Open Set Classification This is the official pytorch implementation of t

Alibaba Cloud 5 Nov 14, 2022
《LXMERT: Learning Cross-Modality Encoder Representations from Transformers》(EMNLP 2020)

The Most Important Thing. Our code is developed based on: LXMERT: Learning Cross-Modality Encoder Representations from Transformers

53 Dec 16, 2022
Pseudo lidar - (CVPR 2019) Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving This paper has been accpeted by Conference o

Yan Wang 881 Dec 27, 2022
Agent-based model simulator for air quality and pandemic risk assessment in architectural spaces

Agent-based model simulation for air quality and pandemic risk assessment in architectural spaces. User Guide archABM is a fast and open source agent-

Vicomtech 10 Dec 05, 2022
ImageNet Adversarial Image Evaluation

ImageNet Adversarial Image Evaluation This repository contains the code and some materials used in the experimental work presented in the following pa

Utku Ozbulak 11 Dec 26, 2022
Using deep learning model to detect breast cancer.

Breast-Cancer-Detection Breast cancer is the most frequent cancer among women, with around one in every 19 women at risk. The number of cases of breas

1 Feb 13, 2022
BiSeNet based on pytorch

BiSeNet BiSeNet based on pytorch 0.4.1 and python 3.6 Dataset Download CamVid dataset from Google Drive or Baidu Yun(6xw4). Pretrained model Download

367 Dec 26, 2022
Fast Soft Color Segmentation

Fast Soft Color Segmentation

3 Oct 29, 2022
A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation

A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation

196 Jan 05, 2023
Fashion Recommender System With Python

Fashion-Recommender-System Thr growing e-commerce industry presents us with a la

Omkar Gawade 2 Feb 02, 2022
Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently

Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently This repository is the official implementat

VITA 4 Dec 20, 2022
PyTorch Autoencoders - Implementing a Variational Autoencoder (VAE) Series in Pytorch.

PyTorch Autoencoders Implementing a Variational Autoencoder (VAE) Series in Pytorch. Inspired by this repository Model List check model paper conferen

Subin An 8 Nov 21, 2022
This is the repository for Learning to Generate Piano Music With Sustain Pedals

SusPedal-Gen This is the official repository of Learning to Generate Piano Music With Sustain Pedals Demo Page Dataset The dataset used in this projec

Joann Ching 12 Sep 02, 2022
Implementation of Feedback Transformer in Pytorch

Feedback Transformer - Pytorch Simple implementation of Feedback Transformer in Pytorch. They improve on Transformer-XL by having each token have acce

Phil Wang 93 Oct 04, 2022
In this project we predict the forest cover type using the cartographic variables in the training/test datasets.

Kaggle Competition: Forest Cover Type Prediction In this project we predict the forest cover type (the predominant kind of tree cover) using the carto

Marianne Joy Leano 1 Mar 15, 2022
CCCL: Contrastive Cascade Graph Learning.

CCGL: Contrastive Cascade Graph Learning This repo provides a reference implementation of Contrastive Cascade Graph Learning (CCGL) framework as descr

Xovee Xu 19 Dec 05, 2022
NEATEST: Evolving Neural Networks Through Augmenting Topologies with Evolution Strategy Training

NEATEST: Evolving Neural Networks Through Augmenting Topologies with Evolution Strategy Training

Göktuğ Karakaşlı 16 Dec 05, 2022
An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.

Bottom-Up and Top-Down Attention for Visual Question Answering An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge. The

Hengyuan Hu 731 Jan 03, 2023