Learning Fair Node Representations with Graph Counterfactual Fairness

TL;DR

This paper introduces a new notion of graph counterfactual fairness that accounts for biases caused by sensitive attributes of nodes, neighbors, and graph structure, and proposes a framework using counterfactual data augmentation to learn fair node representations.

Contribution

It proposes a novel graph counterfactual fairness concept and a framework leveraging counterfactual data augmentation to mitigate biases in node representations.

Findings

Outperforms state-of-the-art baselines in fairness metrics.

Achieves comparable prediction accuracy to existing methods.

Effectively mitigates biases caused by sensitive attributes in graphs.

Abstract

Fair machine learning aims to mitigate the biases of model predictions against certain subpopulations regarding sensitive attributes such as race and gender. Among the many existing fairness notions, counterfactual fairness measures the model fairness from a causal perspective by comparing the predictions of each individual from the original data and the counterfactuals. In counterfactuals, the sensitive attribute values of this individual had been modified. Recently, a few works extend counterfactual fairness to graph data, but most of them neglect the following facts that can lead to biases: 1) the sensitive attributes of each node's neighbors may causally affect the prediction w.r.t. this node; 2) the sensitive attributes may causally affect other features and the graph structure. To tackle these issues, in this paper, we propose a novel fairness notion - graph counterfactual fairness, which considers the biases led by the above facts. To learn node representations towards graph counterfactual fairness, we propose a novel framework based on counterfactual data augmentation. In this framework, we generate counterfactuals corresponding to perturbations on each node's and their neighbors' sensitive attributes. Then we enforce fairness by minimizing the discrepancy between the representations learned from the original graph and the counterfactuals for each node. Experiments on both synthetic and real-world graphs show that our framework outperforms the state-of-the-art baselines in graph counterfactual fairness, and also achieves comparable prediction performance.