Towards Fair Graph Neural Networks via Graph Counterfactual without Sensitive Attributes

TL;DR

This paper introduces Fairwos, a novel framework for fair graph neural networks that does not require sensitive attributes by generating pseudo-sensitive attributes and leveraging graph counterfactuals to improve fairness.

Contribution

The paper proposes a new method to achieve fairness in GNNs without sensitive attributes, using pseudo-sensitive attribute generation and counterfactual strategies, supported by theoretical analysis.

Findings

Outperforms state-of-the-art methods on six datasets

Balances fairness and utility effectively

Demonstrates theoretical link between pseudo-sensitive attributes and fairness

Abstract

Graph-structured data is ubiquitous in today's connected world, driving extensive research in graph analysis. Graph Neural Networks (GNNs) have shown great success in this field, leading to growing interest in developing fair GNNs for critical applications. However, most existing fair GNNs focus on statistical fairness notions, which may be insufficient when dealing with statistical anomalies. Hence, motivated by causal theory, there has been growing attention to mitigating root causes of unfairness utilizing graph counterfactuals. Unfortunately, existing methods for generating graph counterfactuals invariably require the sensitive attribute. Nevertheless, in many real-world applications, it is usually infeasible to obtain sensitive attributes due to privacy or legal issues, which challenge existing methods. In this paper, we propose a framework named Fairwos (improving Fairness without sensitive attributes). In particular, we first propose a mechanism to generate pseudo-sensitive attributes to remedy the problem of missing sensitive attributes, and then design a strategy for finding graph counterfactuals from the real dataset. To train fair GNNs, we propose a method to ensure that the embeddings from the original data are consistent with those from the graph counterfactuals, and dynamically adjust the weight of each pseudo-sensitive attribute to balance its contribution to fairness and utility. Furthermore, we theoretically demonstrate that minimizing the relation between these pseudo-sensitive attributes and the prediction can enable the fairness of GNNs. Experimental results on six real-world datasets show that our approach outperforms state-of-the-art methods in balancing utility and fairness.