FAROS: Fair Graph Generation via Attribute Switching Mechanisms

TL;DR

FAROS introduces a novel method for fair graph generation by dynamically switching node attributes during the diffusion process, effectively balancing fairness and accuracy without retraining the model.

Contribution

The paper presents FAROS, a new framework that enforces fairness in graph generation through attribute switching during diffusion, avoiding retraining and improving fairness-accuracy trade-offs.

Findings

Reduces fairness discrepancies in generated graphs.

Maintains or improves accuracy compared to baselines.

Achieves better fairness-accuracy trade-offs under Pareto optimality.

Abstract

Recent advancements in graph diffusion models (GDMs) have enabled the synthesis of realistic network structures, yet ensuring fairness in the generated data remains a critical challenge. Existing solutions attempt to mitigate bias by re-training the GDMs with ad-hoc fairness constraints. Conversely, with this work, we propose FAROS, a novel FAir graph geneRatiOn framework leveraging attribute Switching mechanisms and directly running in the generation process of the pre-trained GDM. Technically, our approach works by altering nodes' sensitive attributes during the generation. To this end, FAROS calculates the optimal fraction of switching nodes, and selects the diffusion step to perform the switch by setting tailored multi-criteria constraints to preserve the node-topology profile from the original distribution (a proxy for accuracy) while ensuring the edge independence on the sensitive attributes for the generated graph (a proxy for fairness). Our experiments on benchmark datasets for link prediction demonstrate that the proposed approach effectively reduces fairness discrepancies while maintaining comparable (or even higher) accuracy performance to other similar baselines. Noteworthy, FAROS is also able to strike a better accuracy-fairness trade-off than other competitors in some of the tested settings under the Pareto optimality concept, demonstrating the effectiveness of the imposed multi-criteria constraints.