arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.02005cs.LGcs.AIcs.SI
收藏

通过反事实干预缓解图扩散中的拓扑偏见

Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

Purdue University(帕克大学);The Pennsylvania State University(宾夕法尼亚州立大学)

Wendi Wang, Jiaxi Yang, Yongkang Du, Lu Lin

AI总结:

FairGDiff通过反事实干预缓解图扩散中的拓扑偏见,平衡公平性与实用性,优于现有方法。

摘要:

图扩散模型在图生成任务中获得了显著关注,但它们往往继承并放大了敏感属性(如性别、年龄、地区)的拓扑偏见,导致不公平的合成图。现有的公平图生成使用扩散模型的方法局限于特定的图基应用,需要完整的标签或同时更新图结构和节点属性,使其不适合一般使用。为缓解这些限制,我们通过直接在图拓扑上应用去偏方法,提出公平图扩散模型(FairGDiff),这是一种基于反事实的一步解决方案,能够在缓解拓扑偏见的同时平衡公平性和实用性。具体来说,我们构建了一个因果模型,以捕捉敏感属性、偏见链接形成和生成图结构之间的关系。通过回答反事实问题“如果敏感属性不同,图结构会改变吗?”我们估计一个无偏的处理,并将其纳入扩散过程。FairGDiff将反事实学习整合到正向扩散和反向去噪中,确保生成的图独立于敏感属性,同时保持结构完整性。在真实世界数据集上的广泛实验表明,FairGDiff在公平性与实用性之间实现了更优的权衡,优于现有公平图生成方法,同时保持可扩展性。

英文摘要:

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 graphs. Existing fair graph generation using diffusion models is limited to specific graph-based applications with complete labels or requires simultaneous updates for graph structure and node attributes, making them unsuitable for general usage. To relax these limitations by applying the debiasing method directly on graph topology, we propose Fair Graph Diffusion Model (FairGDiff), a counterfactual-based one-step solution that mitigates topology biases while balancing fairness and utility. In detail, we construct a causal model to capture the relationship between sensitive attributes, biased link formation, and the generated graph structure. By answering the counterfactual question "Would the graph structure change if the sensitive attribute were different?", we estimate an unbiased treatment and incorporate it into the diffusion process. FairGDiff integrates counterfactual learning into both forward diffusion and backward denoising, ensuring that the generated graphs are independent of sensitive attributes while preserving structural integrity. Extensive experiments on real-world datasets demonstrate that FairGDiff achieves a superior trade-off between fairness and utility, outperforming existing fair graph generation methods while maintaining scalability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑