Towards Fair Graph Neural Networks via Graph Counterfactual

TL;DR

This paper introduces CAF, a causal framework for fair graph neural networks that selects realistic counterfactuals from training data to mitigate bias and improve fairness in node classification.

Contribution

It proposes a novel causal approach for fair GNNs by selecting realistic counterfactuals from training data, addressing limitations of previous methods.

Findings

CAF effectively reduces bias in GNNs.

Experimental results show improved fairness and accuracy.

The framework outperforms existing fairness-aware GNN methods.

Abstract

Graph neural networks have shown great ability in representation (GNNs) learning on graphs, facilitating various tasks. Despite their great performance in modeling graphs, recent works show that GNNs tend to inherit and amplify the bias from training data, causing concerns of the adoption of GNNs in high-stake scenarios. Hence, many efforts have been taken for fairness-aware GNNs. However, most existing fair GNNs learn fair node representations by adopting statistical fairness notions, which may fail to alleviate bias in the presence of statistical anomalies. Motivated by causal theory, there are several attempts utilizing graph counterfactual fairness to mitigate root causes of unfairness. However, these methods suffer from non-realistic counterfactuals obtained by perturbation or generation. In this paper, we take a causal view on fair graph learning problem. Guided by the casual analysis, we propose a novel framework CAF, which can select counterfactuals from training data to avoid non-realistic counterfactuals and adopt selected counterfactuals to learn fair node representations for node classification task. Extensive experiments on synthetic and real-world datasets show the effectiveness of CAF. Our code is available at https://github.com/TimeLovercc/CAF-GNN.