FnRGNN: Distribution-aware Fairness in Graph Neural Network

TL;DR

FnRGNN introduces a multi-level fairness-aware framework for GNN-based node regression, addressing continuous data bias and improving fairness without performance loss.

Contribution

It proposes a novel in-processing method combining structure, representation, and prediction-level interventions for fairness in GNN regression tasks.

Findings

Reduces group disparities in real-world datasets

Maintains high prediction performance

Effective across complex graph topologies

Abstract

Graph Neural Networks (GNNs) excel at learning from structured data, yet fairness in regression tasks remains underexplored. Existing approaches mainly target classification and representation-level debiasing, which cannot fully address the continuous nature of node-level regression. We propose FnRGNN, a fairness-aware in-processing framework for GNN-based node regression that applies interventions at three levels: (i) structure-level edge reweighting, (ii) representation-level alignment via MMD, and (iii) prediction-level normalization through Sinkhorn-based distribution matching. This multi-level strategy ensures robust fairness under complex graph topologies. Experiments on four real-world datasets demonstrate that FnRGNN reduces group disparities without sacrificing performance. Code is available at https://github.com/sybeam27/FnRGNN.