Learning Fair Graph Representations with Multi-view Information Bottleneck

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Chuxun, Cheng, Debo, Chen, Qingfeng, Gan, Jiangzhang, Li, Jiuyong, Liu, Lin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917049187434496
author Liu, Chuxun
Cheng, Debo
Chen, Qingfeng
Gan, Jiangzhang
Li, Jiuyong
Liu, Lin
author_facet Liu, Chuxun
Cheng, Debo
Chen, Qingfeng
Gan, Jiangzhang
Li, Jiuyong
Liu, Lin
contents Graph neural networks (GNNs) excel on relational data by passing messages over node features and structure, but they can amplify training data biases, propagating discriminatory attributes and structural imbalances into unfair outcomes. Many fairness methods treat bias as a single source, ignoring distinct attribute and structure effects and leading to suboptimal fairness and utility trade-offs. To overcome this challenge, we propose FairMIB, a multi-view information bottleneck framework designed to decompose graphs into feature, structural, and diffusion views for mitigating complexity biases in GNNs. Especially, the proposed FairMIB employs contrastive learning to maximize cross-view mutual information for bias-free representation learning. It further integrates multi-perspective conditional information bottleneck objectives to balance task utility and fairness by minimizing mutual information with sensitive attributes. Additionally, FairMIB introduces an inverse probability-weighted (IPW) adjacency correction in the diffusion view, which reduces the spread of bias propagation during message passing. Experiments on five real-world benchmark datasets demonstrate that FairMIB achieves state-of-the-art performance across both utility and fairness metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25096
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Fair Graph Representations with Multi-view Information Bottleneck
Liu, Chuxun
Cheng, Debo
Chen, Qingfeng
Gan, Jiangzhang
Li, Jiuyong
Liu, Lin
Machine Learning
Artificial Intelligence
Graph neural networks (GNNs) excel on relational data by passing messages over node features and structure, but they can amplify training data biases, propagating discriminatory attributes and structural imbalances into unfair outcomes. Many fairness methods treat bias as a single source, ignoring distinct attribute and structure effects and leading to suboptimal fairness and utility trade-offs. To overcome this challenge, we propose FairMIB, a multi-view information bottleneck framework designed to decompose graphs into feature, structural, and diffusion views for mitigating complexity biases in GNNs. Especially, the proposed FairMIB employs contrastive learning to maximize cross-view mutual information for bias-free representation learning. It further integrates multi-perspective conditional information bottleneck objectives to balance task utility and fairness by minimizing mutual information with sensitive attributes. Additionally, FairMIB introduces an inverse probability-weighted (IPW) adjacency correction in the diffusion view, which reduces the spread of bias propagation during message passing. Experiments on five real-world benchmark datasets demonstrate that FairMIB achieves state-of-the-art performance across both utility and fairness metrics.
title Learning Fair Graph Representations with Multi-view Information Bottleneck
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.25096