Learning Fair Representations for Recommendation: A Graph-based Perspective, WWW2021

Last update: Oct 26, 2022

Overview

FairGo WWW2021

Learning Fair Representations for Recommendation: A Graph-based Perspective

As a key application of artificial intelligence, recommender systems are among the most pervasive computer aided systems to help users find potential items of interests. Recently, researchers paid considerable attention to fairness issues for artificial intelligence applications. Most of these approaches assumed independence of instances, and designed sophisticated models to eliminate the sensitive information to facilitate fairness. However, recommender systems differ greatly from these approaches as users and items naturally form a user-item bipartite graph, and are collaboratively correlated in the graph structure. In this paper, we propose a novel graph based technique for ensuring fairness of any recommendation models. Here, the fairness requirements refer to not exposing sensitive feature set in the user modeling process. Specifically, given the original embeddings from any recommendation models, we learn a composition of filters that transform each user's and each item's original embeddings into a filtered embedding space based on the sensitive feature set. For each user, this transformation is achieved under the adversarial learning of a user-centric graph, in order to obfuscating each sensitive feature between both the filtered user embedding and the sub graph structures of this user. Finally, extensive experimental results clearly show the effectiveness of our proposed model for fair recommendation.

We provide PyTorch implementations for FairGo model.

Prerequisites

PyTorch
Python 3.5
CPU or NVIDIA GPU + CUDA CuDNN

Getting Started

Installation

Clone this repo:

git clone https://github.com/newlei/FairGo.git
cd FairGo
cd code

Code

Code on MovieLens-1M. Please open “code/code_ml”.

Code on Lastfm-360K. Please open “code/code_lastfm”.

Datasets

In order to speed up model training, the original dataset was processed to form a variety of intermediate data. Because these intermediate data of MovieLens-1M and Lastfm-360K occupy too much space, it cannot be completely put on GitHub which allows max file size to 100 MB. Therefore, some intermediate data is missing. We release all data in link.

We release all data in link.

Citation

If you find this useful for your research, please kindly cite the following paper that crawal and analyze the data.

@article{wu2021learn,
  title={Learning Fair Representations for Recommendation: A Graph-based Perspective},
  author={Le Wu, Lei Chen, Pengyang Shao, Richang Hong, Xiting Wang and Meng Wang}
  journal={WWW},
  year={2021}
}

Besides, you may find these following works are useful for understanding GCN-based recommendation.

@article{chen2019revis,
  title={Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach},
  author={Lei, Chen and Le, Wu and  Richang, Hong and Kun, Zhang and Meng, Wang}
  journal={AAAI},
  year={2019}
}

Acknowledgments

We thank LMC lab. of Hefei University of Technology

You might also like...

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

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

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

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

FAIR Enough Metrics is an API for various FAIR Metrics Tests, written in python

☑️ FAIR Enough metrics for research FAIR Enough Metrics is an API for various FAIR Metrics Tests, written in python, conforming to the specifications

3 Jul 6, 2022

fair-test is a library to build and deploy FAIR metrics tests APIs supporting the specifications used by the FAIRMetrics working group.

☑️ FAIR test fair-test is a library to build and deploy FAIR metrics tests APIs supporting the specifications used by the FAIRMetrics working group. I

6 Oct 30, 2022

Product-based-recommendation-system - A product based recommendation system which uses Machine learning algorithm such as KNN and cosine similarity

Product-based-recommendation-system A product based recommendation system which

2 Feb 15, 2022

Fair Recommendation in Two-Sided Platforms

1 Nov 10, 2021

A PyTorch implementation of "Semi-Supervised Graph Classification: A Hierarchical Graph Perspective" (WWW 2019)

SEAL ⠀⠀⠀ A PyTorch implementation of Semi-Supervised Graph Classification: A Hierarchical Graph Perspective (WWW 2019) Abstract Node classification an

202 Dec 27, 2022

Recommendationsystem - Movie-recommendation - matrixfactorization colloborative filtering recommendation system user

recommendationsystem matrixfactorization colloborative filtering recommendation

1 Jan 1, 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

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Introduction PyTorch3D provides efficient, reusable components for 3D Computer Vision research with PyTorch. Key features include: Data structure for

6.8k Jan 1, 2023

Code for KDD'20 "An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph"

Heterogeneous INteract and aggreGatE (GraphHINGE) This is a pytorch implementation of GraphHINGE model. This is the experiment code in the following w

69 Nov 24, 2022

Codes for CIKM'21 paper 'Self-Supervised Graph Co-Training for Session-based Recommendation'.

COTREC Codes for CIKM'21 paper 'Self-Supervised Graph Co-Training for Session-based Recommendation'. Requirements: Python 3.7, Pytorch 1.6.0 Best Hype

42 Dec 9, 2022

Official public repository of paper "Intention Adaptive Graph Neural Network for Category-Aware Session-Based Recommendation"

Intention Adaptive Graph Neural Network (IAGNN) This is the official repository of paper Intention Adaptive Graph Neural Network for Category-Aware Se

9 Nov 22, 2022

Comments

请求数据处理文件

您好！拜读了您的paper和部分code，感受颇深，我想尝试复现效果并在此基础上做一些改进。但是我从您的代码和数据集链接中并未找到完整的数据集处理文件（只看到一小部分处理lastfm的data.py，而且还很不完整，只是提取了user和item的属性部分），希望您可以上传一下处理数据集的py文件，感谢！！！

opened by TangJiakai 3
Some questions about the optimization process
Hi, I am reading your paper and codes, it is very interesting work and I would like to take your work as a baseline. But I have some questions about the implementation.

(1) when updating the filters, it seems that there are two goals -- minimize the recommendation loss and maximize the classification loss. In your paper, a hyperparameter $\lambda$ is used to combine the two losses together to realize the goals. But in your codes, it seems that the two corresponding losses are optimized separately, and the classification is only updated one batch as following. Which one should I make use of?

for user_batch, rating_batch, item_batch in train_loader: user_batch = user_batch.cuda() rating_batch = rating_batch.cuda() item_batch = item_batch.cuda() d_g_l_get = model(copy.deepcopy(pos_adj),user_batch,rating_batch,item_batch) # d_g_l_get = model(copy.deepcopy(pos_adj),copy.deepcopy(pos_adj),user,item_i, item_j) _,f_l,d_l = d_g_l_get loss_current[0].append(f_l.item()) # loss_current[1].append(d_l.item()) f_optimizer.zero_grad() f_l.backward() f_optimizer.step() # continue d_g_l_get = model(copy.deepcopy(pos_adj),user_batch,rating_batch,item_batch) _,f_l,d_l = d_g_l_get loss_current[1].append(d_l.item()) f_optimizer.zero_grad() d_l.backward() f_optimizer.step()

(2) if the prediction is not computed by inner product instead of neural networks(NN), do I need to update the NN together when I update the filters?

Looking forward to your reply!
opened by zyang1580 1

Learning Fair Representations for Recommendation: A Graph-based Perspective, WWW2021

Related tags

Overview

FairGo WWW2021

Prerequisites

Getting Started

Installation

Code

Datasets

Citation

Acknowledgments

You might also like...

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

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

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

Elliot is a comprehensive recommendation framework that analyzes the recommendation problem from the researcher's perspective.

FAIR Enough Metrics is an API for various FAIR Metrics Tests, written in python

fair-test is a library to build and deploy FAIR metrics tests APIs supporting the specifications used by the FAIRMetrics working group.

Product-based-recommendation-system - A product based recommendation system which uses Machine learning algorithm such as KNN and cosine similarity

Fair Recommendation in Two-Sided Platforms

A PyTorch implementation of "Semi-Supervised Graph Classification: A Hierarchical Graph Perspective" (WWW 2019)

Recommendationsystem - Movie-recommendation - matrixfactorization colloborative filtering recommendation system user

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

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Code for KDD'20 "An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph"

Codes for CIKM'21 paper 'Self-Supervised Graph Co-Training for Session-based Recommendation'.

Official public repository of paper "Intention Adaptive Graph Neural Network for Category-Aware Session-Based Recommendation"

Tensorflow implementation for Self-supervised Graph Learning for Recommendation

GB-CosFace: Rethinking Softmax-based Face Recognition from the Perspective of Open Set Classification

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

Comments

请求数据处理文件

Some questions about the optimization process

Owner

lei

A Python implementation of LightFM, a hybrid recommendation algorithm.

A TensorFlow recommendation algorithm and framework in Python.

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

ToR[e]cSys is a PyTorch Framework to implement recommendation system algorithms

A framework for large scale recommendation algorithms.

Recommendation System to recommend top books from the dataset

An open source movie recommendation WebApp build by movie buffs and mathematicians that uses cosine similarity on the backend.

Books Recommendation With Python

Bert4rec for news Recommendation

Graph Neural Networks for Recommender Systems