BeMap: Balanced Message Passing for Fair Graph Neural Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Xiao, Kang, Jian, Cong, Weilin, Tong, Hanghang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914708450181120
author Lin, Xiao
Kang, Jian
Cong, Weilin
Tong, Hanghang
author_facet Lin, Xiao
Kang, Jian
Cong, Weilin
Tong, Hanghang
contents Fairness in graph neural networks has been actively studied recently. However, existing works often do not explicitly consider the role of message passing in introducing or amplifying the bias. In this paper, we first investigate the problem of bias amplification in message passing. We empirically and theoretically demonstrate that message passing could amplify the bias when the 1-hop neighbors from different demographic groups are unbalanced. Guided by such analyses, we propose BeMap, a fair message passing method, that leverages a balance-aware sampling strategy to balance the number of the 1-hop neighbors of each node among different demographic groups. Extensive experiments on node classification demonstrate the efficacy of BeMap in mitigating bias while maintaining classification accuracy. The code is available at https://github.com/xiaolin-cs/BeMap.
format Preprint
id arxiv_https___arxiv_org_abs_2306_04107
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle BeMap: Balanced Message Passing for Fair Graph Neural Network
Lin, Xiao
Kang, Jian
Cong, Weilin
Tong, Hanghang
Machine Learning
Artificial Intelligence
Social and Information Networks
Fairness in graph neural networks has been actively studied recently. However, existing works often do not explicitly consider the role of message passing in introducing or amplifying the bias. In this paper, we first investigate the problem of bias amplification in message passing. We empirically and theoretically demonstrate that message passing could amplify the bias when the 1-hop neighbors from different demographic groups are unbalanced. Guided by such analyses, we propose BeMap, a fair message passing method, that leverages a balance-aware sampling strategy to balance the number of the 1-hop neighbors of each node among different demographic groups. Extensive experiments on node classification demonstrate the efficacy of BeMap in mitigating bias while maintaining classification accuracy. The code is available at https://github.com/xiaolin-cs/BeMap.
title BeMap: Balanced Message Passing for Fair Graph Neural Network
topic Machine Learning
Artificial Intelligence
Social and Information Networks
url https://arxiv.org/abs/2306.04107