FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning

TL;DR

FairDrop is a novel biased edge dropout method designed to improve fairness in graph representation learning by counteracting homophily, with minimal impact on accuracy, applicable to various models and evaluated on benchmark tasks.

Contribution

The paper introduces FairDrop, a flexible, efficient biased edge dropout algorithm that enhances fairness in graph learning and can be integrated with existing methods.

Findings

FairDrop improves fairness with minimal accuracy loss.

It can be combined with different graph models.

The method outperforms some state-of-the-art fairness solutions.

Abstract

Graph representation learning has become a ubiquitous component in many scenarios, ranging from social network analysis to energy forecasting in smart grids. In several applications, ensuring the fairness of the node (or graph) representations with respect to some protected attributes is crucial for their correct deployment. Yet, fairness in graph deep learning remains under-explored, with few solutions available. In particular, the tendency of similar nodes to cluster on several real-world graphs (i.e., homophily) can dramatically worsen the fairness of these procedures. In this paper, we propose a novel biased edge dropout algorithm (FairDrop) to counter-act homophily and improve fairness in graph representation learning. FairDrop can be plugged in easily on many existing algorithms, is efficient, adaptable, and can be combined with other fairness-inducing solutions. After describing the general algorithm, we demonstrate its application on two benchmark tasks, specifically, as a random walk model for producing node embeddings, and to a graph convolutional network for link prediction. We prove that the proposed algorithm can successfully improve the fairness of all models up to a small or negligible drop in accuracy, and compares favourably with existing state-of-the-art solutions. In an ablation study, we demonstrate that our algorithm can flexibly interpolate between biasing towards fairness and an unbiased edge dropout. Furthermore, to better evaluate the gains, we propose a new dyadic group definition to measure the bias of a link prediction task when paired with group-based fairness metrics. In particular, we extend the metric used to measure the bias in the node embeddings to take into account the graph structure.