FairNorm: Fair and Fast Graph Neural Network Training

TL;DR

FairNorm is a normalization framework for graph neural networks that enhances fairness towards sensitive groups and accelerates training convergence, addressing bias and efficiency issues in GNNs.

Contribution

This work introduces FairNorm, a novel normalization method that reduces bias and speeds up GNN training through fairness-aware operators with learnable parameters.

Findings

Improves fairness in node classification tasks on real-world networks.

Achieves faster convergence compared to baseline methods.

Demonstrates effectiveness over existing fairness-aware baselines.

Abstract

Graph neural networks (GNNs) have been demonstrated to achieve state-of-the-art for a number of graph-based learning tasks, which leads to a rise in their employment in various domains. However, it has been shown that GNNs may inherit and even amplify bias within training data, which leads to unfair results towards certain sensitive groups. Meanwhile, training of GNNs introduces additional challenges, such as slow convergence and possible instability. Faced with these limitations, this work proposes FairNorm, a unified normalization framework that reduces the bias in GNN-based learning while also providing provably faster convergence. Specifically, FairNorm employs fairness-aware normalization operators over different sensitive groups with learnable parameters to reduce the bias in GNNs. The design of FairNorm is built upon analyses that illuminate the sources of bias in graph-based learning. Experiments on node classification over real-world networks demonstrate the efficiency of the proposed scheme in improving fairness in terms of statistical parity and equal opportunity compared to fairness-aware baselines. In addition, it is empirically shown that the proposed framework leads to faster convergence compared to the naive baseline where no normalization is employed.