FairGAT: Fairness-aware Graph Attention Networks
It addresses fairness issues in graph neural networks for node classification and link prediction, offering an incremental improvement over existing fairness-aware methods.
The paper tackled algorithmic bias in graph attention networks (GATs) by analyzing bias sources and developing FairGAT, a fairness-aware attention design, which improved group fairness measures on real-world networks while maintaining comparable utility to baselines.
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.