Fairness and/or Privacy on Social Graphs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Surma, Bartlomiej, Backes, Michael, Zhang, Yang
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computers and Society Social and Information Networks
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866912258375811072
author	Surma, Bartlomiej Backes, Michael Zhang, Yang
author_facet	Surma, Bartlomiej Backes, Michael Zhang, Yang
contents	Graph Neural Networks (GNNs) have shown remarkable success in various graph-based learning tasks. However, recent studies have raised concerns about fairness and privacy issues in GNNs, highlighting the potential for biased or discriminatory outcomes and the vulnerability of sensitive information. This paper presents a comprehensive investigation of fairness and privacy in GNNs, exploring the impact of various fairness-preserving measures on model performance. We conduct experiments across diverse datasets and evaluate the effectiveness of different fairness interventions. Our analysis considers the trade-offs between fairness, privacy, and accuracy, providing insights into the challenges and opportunities in achieving both fair and private graph learning. The results highlight the importance of carefully selecting and combining fairness-preserving measures based on the specific characteristics of the data and the desired fairness objectives. This study contributes to a deeper understanding of the complex interplay between fairness, privacy, and accuracy in GNNs, paving the way for the development of more robust and ethical graph learning models.
format	Preprint
id	arxiv_https___arxiv_org_abs_2503_02114
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	Fairness and/or Privacy on Social Graphs Surma, Bartlomiej Backes, Michael Zhang, Yang Machine Learning Computers and Society Social and Information Networks Graph Neural Networks (GNNs) have shown remarkable success in various graph-based learning tasks. However, recent studies have raised concerns about fairness and privacy issues in GNNs, highlighting the potential for biased or discriminatory outcomes and the vulnerability of sensitive information. This paper presents a comprehensive investigation of fairness and privacy in GNNs, exploring the impact of various fairness-preserving measures on model performance. We conduct experiments across diverse datasets and evaluate the effectiveness of different fairness interventions. Our analysis considers the trade-offs between fairness, privacy, and accuracy, providing insights into the challenges and opportunities in achieving both fair and private graph learning. The results highlight the importance of carefully selecting and combining fairness-preserving measures based on the specific characteristics of the data and the desired fairness objectives. This study contributes to a deeper understanding of the complex interplay between fairness, privacy, and accuracy in GNNs, paving the way for the development of more robust and ethical graph learning models.
title	Fairness and/or Privacy on Social Graphs
topic	Machine Learning Computers and Society Social and Information Networks
url	https://arxiv.org/abs/2503.02114