FairGAT: Fairness-aware Graph Attention Networks

TL;DR

FairGAT introduces a fairness-aware attention mechanism in graph neural networks to mitigate bias, improving fairness metrics without sacrificing predictive performance on real-world graph tasks.

Contribution

The paper provides a theoretical analysis of bias sources in GATs and proposes FairGAT, a novel attention design that enhances fairness in graph learning.

Findings

FairGAT improves group fairness measures in node classification.

FairGAT maintains comparable utility to existing fairness-aware models.

Experimental results validate the effectiveness of FairGAT on real-world networks.

Abstract

Graphs can facilitate modeling various complex systems such as gene networks and power grids, as well as analyzing the underlying relations within them. Learning over graphs has recently attracted increasing attention, particularly graph neural network-based (GNN) solutions, among which graph attention networks (GATs) have become one of the most widely utilized neural network structures for graph-based tasks. Although it is shown that the use of graph structures in learning results in the amplification of algorithmic bias, the influence of the attention design in GATs on algorithmic bias has not been investigated. Motivated by this, the present study first carries out a theoretical analysis in order to demonstrate the sources of algorithmic bias in GAT-based learning for node classification. Then, a novel algorithm, FairGAT, that leverages a fairness-aware attention design is developed based on the theoretical findings. Experimental results on real-world networks demonstrate that FairGAT improves group fairness measures while also providing comparable utility to the fairness-aware baselines for node classification and link prediction.