Fairness-Aware Graph Representation Learning with Limited Demographic Information

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zichong, Yin, Zhipeng, Yang, Liping, Zhuang, Jun, Yu, Rui, Kong, Qingzhao, Zhang, Wenbin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914219707858944
author Wang, Zichong
Yin, Zhipeng
Yang, Liping
Zhuang, Jun
Yu, Rui
Kong, Qingzhao
Zhang, Wenbin
author_facet Wang, Zichong
Yin, Zhipeng
Yang, Liping
Zhuang, Jun
Yu, Rui
Kong, Qingzhao
Zhang, Wenbin
contents Ensuring fairness in Graph Neural Networks is fundamental to promoting trustworthy and socially responsible machine learning systems. In response, numerous fair graph learning methods have been proposed in recent years. However, most of them assume full access to demographic information, a requirement rarely met in practice due to privacy, legal, or regulatory restrictions. To this end, this paper introduces a novel fair graph learning framework that mitigates bias in graph learning under limited demographic information. Specifically, we propose a mechanism guided by partial demographic data to generate proxies for demographic information and design a strategy that enforces consistent node embeddings across demographic groups. In addition, we develop an adaptive confidence strategy that dynamically adjusts each node's contribution to fairness and utility based on prediction confidence. We further provide theoretical analysis demonstrating that our framework, FairGLite, achieves provable upper bounds on group fairness metrics, offering formal guarantees for bias mitigation. Through extensive experiments on multiple datasets and fair graph learning frameworks, we demonstrate the framework's effectiveness in both mitigating bias and maintaining model utility.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13540
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fairness-Aware Graph Representation Learning with Limited Demographic Information
Wang, Zichong
Yin, Zhipeng
Yang, Liping
Zhuang, Jun
Yu, Rui
Kong, Qingzhao
Zhang, Wenbin
Machine Learning
Computers and Society
Ensuring fairness in Graph Neural Networks is fundamental to promoting trustworthy and socially responsible machine learning systems. In response, numerous fair graph learning methods have been proposed in recent years. However, most of them assume full access to demographic information, a requirement rarely met in practice due to privacy, legal, or regulatory restrictions. To this end, this paper introduces a novel fair graph learning framework that mitigates bias in graph learning under limited demographic information. Specifically, we propose a mechanism guided by partial demographic data to generate proxies for demographic information and design a strategy that enforces consistent node embeddings across demographic groups. In addition, we develop an adaptive confidence strategy that dynamically adjusts each node's contribution to fairness and utility based on prediction confidence. We further provide theoretical analysis demonstrating that our framework, FairGLite, achieves provable upper bounds on group fairness metrics, offering formal guarantees for bias mitigation. Through extensive experiments on multiple datasets and fair graph learning frameworks, we demonstrate the framework's effectiveness in both mitigating bias and maintaining model utility.
title Fairness-Aware Graph Representation Learning with Limited Demographic Information
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2511.13540