paper-with-me

홈 › Papers

FAROS: Fair Graph Generation via Attribute Switching Mechanisms

2025-07-04 · Abdennacer Badaoui, Oussama Kharouiche, Hatim Mrabet, Daniele Malitesta, Fragkiskos D. Malliaros arxiv

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.

📄 PDF Abstract BibTeX arXiv:2507.03728

Code (0)

등록된 구현이 없습니다.

Tasks

Graph GenerationLink Prediction

Similar Papers 제목 키워드 기반

Fair Sampling in Diffusion Models through Switching Mechanism

2024-01-06 · Yujin Choi, Jinseong Park, Hoki Kim, Jaewook Lee 외

Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the tr…

AttributeFairness

OMSN and FAROS: OCTA Microstructure Segmentation Network and Fully Annotated Retinal OCTA Segmentation Dataset

2022-12-26 · Peng Xiao, Xiaodong Hu, Ke Ma, Gengyuan Wang 외

The lack of efficient segmentation methods and fully-labeled datasets limits the comprehensive assessment of optical coherence tomography angiography (OCTA) microstructures like retinal vessel network (RVN) and foveal av…

DecoderSegmentation

Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

2026-03-02 · Wendi Wang, Jiaxi Yang, Yongkang Du, Lu Lin arxiv

Graph diffusion models have gained significant attention in graph generation tasks, but they often inherit and amplify topology biases from sensitive attributes (e.g. gender, age, region), leading to unfair synthetic gra…

Graph Generation

Detecting and Mitigating Bias by Treating Fairness as a Symmetry Operation

2026-06-02 · Nishit Singh arxiv

Machine learning systems deployed in high stakes socioeconomic settings routinely display bias. We formalize bias as a symmetry breaking operation: a classifier is fair if its outputs remain invariant under the counterfa…

Fair Attribute Completion on Graph with Missing Attributes

2023-02-25 · Dongliang Guo, Zhixuan Chu, Sheng Li

Tackling unfairness in graph learning models is a challenging task, as the unfairness issues on graphs involve both attributes and topological structures. Existing work on fair graph learning simply assumes that attribut…

AttributeFairnessGraph Learning