FAROS：通过属性切换机制实现公平图生成

摘要

近期图扩散模型（GDMs）的进展已能合成逼真的网络结构，但确保生成数据的公平性仍是一项关键挑战。现有解决方案试图通过重新训练GDMs并加入临时公平性约束来缓解偏差。与此不同，本研究提出了FAROS，一种新颖的公平图生成框架，它利用属性切换机制，直接在预训练GDMs的生成过程中运行。从技术上讲，我们的方法通过在生成过程中改变节点的敏感属性来实现这一目标。为此，FAROS计算了最优的节点切换比例，并通过设定定制的多准则约束来选择执行切换的扩散步骤，以保持原始分布中的节点拓扑特征（作为准确性的代理），同时确保生成图中边对敏感属性的独立性（作为公平性的代理）。我们在链接预测基准数据集上的实验表明，所提出的方法有效减少了公平性差异，同时保持了与其他类似基线相当（甚至更高）的准确性表现。值得注意的是，在帕累托最优概念下，FAROS在某些测试场景中能够实现比其他竞争者更好的准确性-公平性权衡，这证明了所施加的多准则约束的有效性。

English

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.

FAROS：通过属性切换机制实现公平图生成

FAROS: Fair Graph Generation via Attribute Switching Mechanisms

摘要

Support