FAROS: Fair Graph Generation via Attribute Switching Mechanisms

2025-07-04

AI Summary

Existing graph diffusion models (GDMs) generate high-fidelity network structures but lack fairness guarantees. This paper proposes a post-hoc, retraining-free fairness enhancement method: during GDM sampling, it dynamically perturbs node-sensitive attributes while enforcing edge independence constraints and preserving the joint node-topology distribution—thereby jointly optimizing fairness and structural fidelity. Its core innovation lies in the first principled control of attribute perturbation ratio and timing to navigate the Pareto frontier between fairness and link prediction accuracy. Experiments across multiple benchmark datasets demonstrate that our method significantly reduces fairness disparities (e.g., ADG, SPD) while maintaining or improving prediction accuracy. The resulting fairness–accuracy trade-off consistently outperforms state-of-the-art methods.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Diffusion Models for Vision
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Ensuring fairness in graph generation models
• Reducing bias without retraining diffusion models
• Balancing accuracy and fairness in generated graphs

Innovation

• Switches node attributes during graph generation
• Calculates optimal node switching fraction
• Sets multi-criteria constraints for fairness