Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networks

TL;DR

This paper introduces DEA, a novel fine-tuning method for graph neural networks that enforces fairness in link prediction by dropping unfair edges and adapting the model with covariance-based constraints, improving both fairness and accuracy.

Contribution

DEA is the first approach to combine edge dropping and learnable adjacency matrix adaptation with fairness constraints for GNNs in link prediction.

Findings

Improves fairness in link prediction on five real-world datasets.

Enhances accuracy while enforcing fairness constraints.

Ablation study shows the training algorithm boosts performance.

Abstract

The rise of graph representation learning as the primary solution for many different network science tasks led to a surge of interest in the fairness of this family of methods. Link prediction, in particular, has a substantial social impact. However, link prediction algorithms tend to increase the segregation in social networks by disfavoring the links between individuals in specific demographic groups. This paper proposes a novel way to enforce fairness on graph neural networks with a fine-tuning strategy. We Drop the unfair Edges and, simultaneously, we Adapt the model's parameters to those modifications, DEA in short. We introduce two covariance-based constraints designed explicitly for the link prediction task. We use these constraints to guide the optimization process responsible for learning the new "fair" adjacency matrix. One novelty of DEA is that we can use a discrete yet learnable adjacency matrix in our fine-tuning. We demonstrate the effectiveness of our approach on five real-world datasets and show that we can improve both the accuracy and the fairness of the link prediction tasks. In addition, we present an in-depth ablation study demonstrating that our training algorithm for the adjacency matrix can be used to improve link prediction performances during training. Finally, we compute the relevance of each component of our framework to show that the combination of both the constraints and the training of the adjacency matrix leads to optimal performances.