2025-01-14-wang25e.md

title	Counterfacual Fairness for Graph Neural Networks with Limited and Privacy Protected Sensitive Attributes
booktitle	Proceedings of the 16th Asian Conference on Machine Learning
year	2025
volume	260
series	Proceedings of Machine Learning Research
month	0
publisher	PMLR
pdf	https://raw.githubusercontent.com/mlresearch/v260/main/assets/wang25e/wang25e.pdf
url	https://proceedings.mlr.press/v260/wang25e.html
openreview	R3ufV8D75Z
abstract	Graph Neural Networks (GNNs) have shown outstanding performance in learning graph representations, which increases their application in high-risk areas. However, GNNs may inherit biases from the graph data and make unfair predictions towards the protected sub-groups. To eliminate bias, a natural idea is to achieve counterfactual fairness from a causal perspective. Concretely, counterfactual fairness requires sufficient sensitive attributes as guidance, which is infeasible in the real world. The reason is that users with various privacy preferences may selectively publish their sensitive attributes and only limited sensitive attributes can be collected. Besides, the users who publish sensitive attributes still face privacy risks. In this paper, we first consider the situation in which the sensitive attributes are limited and propose a framework called PCFGR (Partially observed sensitive Attributes in Counterfactual Fair Graph Representation Learning) to learn fair graph representation from limited sensitive attributes. The framework trains a sensitive attribute estimator, which is applied to provide sufficient and accurate sensitive attributes. With these sensitive attributes, it can generate counterfactuals and eliminate the bias efficiently. Secondly, we aim to protect the privacy of the sensitive attributes and further propose PCFGR$\backslash$D. Specifically, PCFGR$\backslash$D first perturbs the sensitive attributes using Local Differential Privacy (LDP). Then it employs forward correction loss to train an accurate sensitive attributes estimator. We conduct extensive experiments and the experiment results show that it outperforms other alternatives in balancing utility and fairness.
layout	inproceedings
issn	2640-3498
id	wang25e
tex_title	Counterfacual Fairness for Graph Neural Networks with Limited and Privacy Protected Sensitive Attributes
firstpage	719
lastpage	734
page	719-734
order	719
cycles	false
bibtex_editor	Nguyen, Vu and Lin, Hsuan-Tien
editor	given family Vu Nguyen given family Hsuan-Tien Lin
bibtex_author	Wang, Xuemin and Wang, Lei and Gu, Tianlong and Bao, Xuguang
author	given family Xuemin Wang given family Lei Wang given family Tianlong Gu given family Xuguang Bao
date	2025-01-14
address
container-title	Proceedings of the 16th Asian Conference on Machine Learning
genre	inproceedings
issued	date-parts 2025 1 14
extras