arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.00595cs.LGcs.AI
收藏

通过公平感知子图扩散实现无偏图神经网络学习

Unbiased GNN Learning via Fairness-Aware Subgraph Diffusion

School of Computer Science, Carleton University(卡尔顿大学计算机科学学院)

Abdullah Alchihabi, Yuhong Guo

AI总结:

本文提出公平感知子图扩散方法FASD,通过随机微分方程驱动的生成式扩散过程对采样子图进行去偏,再在去偏子图上进行GNN学习,从而在多个基准数据集上实现优于现有公平GNN基线的无偏节点预测。

摘要:

图神经网络(GNNs)在多个领域中处理各类图相关任务时展现出了显著的效果。然而,一个重要的挑战在于它们倾向于生成有偏的预测,尤其是在涉及年龄和性别等敏感节点属性时。这些存在于许多机器学习模型中的偏差,在GNNs中由于消息传递机制而被进一步放大,因为该机制允许节点之间相互影响,从而使公平预测的任务变得尤为困难。这一问题在模型公平性至关重要的关键领域中尤为突出。在本文中,我们提出了一种新颖的生成式公平感知子图扩散(FASD)方法,用于实现无偏的GNN学习。该方法首先从原始大型输入图中策略性地采样小子图,然后基于随机微分方程(SDEs),通过生成式公平感知图扩散过程对子图进行去偏处理。为了有效扩散输入数据中的不公平性,我们在前向扩散过程中向子图引入额外的对抗性偏差扰动,并训练基于分数的模型来预测这些施加的扰动,使其能够学习数据中存在的偏差的潜在动态。随后,利用训练好的基于分数的模型,通过反向扩散过程进一步对原始子图样本进行去偏。最后,FASD通过在去偏后的子图上执行标准的GNN学习,在输入图上产生公平的节点预测。实验结果表明,所提出的方法在多个基准数据集上优于最先进的公平GNN基线方法。

英文摘要:

Graph Neural Networks (GNNs) have demonstrated remarkable efficacy in tackling a wide array of graph-related tasks across diverse domains. However, a significant challenge lies in their propensity to generate biased predictions, particularly with respect to sensitive node attributes such as age and gender. These biases, inherent in many machine learning models, are amplified in GNNs due to the message-passing mechanism, which allows nodes to influence each other, rendering the task of making fair predictions notably challenging. This issue is particularly pertinent in critical domains where model fairness holds paramount importance. In this paper, we propose a novel generative Fairness-Aware Subgraph Diffusion (FASD) method for unbiased GNN learning. The method initiates by strategically sampling small subgraphs from the original large input graph, and then proceeds to conduct subgraph debiasing via generative fairness-aware graph diffusion processes based on stochastic differential equations (SDEs). To effectively diffuse unfairness in the input data, we introduce additional adversary bias perturbations to the subgraphs during the forward diffusion process, and train score-based models to predict these applied perturbations, enabling them to learn the underlying dynamics of the biases present in the data. Subsequently, the trained score-based models are utilized to further debias the original subgraph samples through the reverse diffusion process. Finally, FASD induces fair node predictions on the input graph by performing standard GNN learning on the debiased subgraphs. Experimental results demonstrate the superior performance of the proposed method over state-of-the-art Fair GNN baselines across multiple benchmark datasets.

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。

↑