arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.12977cs.LGcs.AI
收藏

图上属性缺失时的公平属性补全

Fair Attribute Completion on Graph with Missing Attributes

University of Georgia(佐治亚大学);Ant Group(蚂蚁集团);University of Virginia(弗吉尼亚大学)

Dongliang Guo, Zhixuan Chu, Sheng Li

AI总结:

提出FairAC方法,利用注意力机制补全缺失属性并同时缓解特征与拓扑不公平性,在基准数据集上以更少精度牺牲取得更优公平性。

摘要:

解决图学习模型中的不公平问题是一项具有挑战性的任务,因为图上的不公平问题既涉及属性又涉及拓扑结构。现有的公平图学习工作简单地假设所有节点的属性都可用于模型训练,然后做出公平的预测。然而,在实践中,由于数据缺失或隐私问题,某些节点的属性可能无法获取,这使得公平图学习更具挑战性。在本文中,我们提出了FairAC,一种公平属性补全方法,用于补充缺失信息并为具有缺失属性的图学习公平的节点嵌入。FairAC采用注意力机制来处理属性缺失问题,同时缓解两种类型的不公平性,即来自属性的特征不公平性和由于属性补全导致的拓扑不公平性。FairAC可以处理各种类型的同构图,并为它们生成公平的嵌入,因此可以应用于大多数下游任务以提高其公平性表现。据我们所知,FairAC是第一个同时解决图属性补全和图不公平性问题的方法。在基准数据集上的实验结果表明,与最先进的公平图学习方法相比,我们的方法在准确性牺牲更少的情况下实现了更好的公平性表现。代码可在以下网址获取:https://github.com/donglgcn/FairAC。

英文摘要:

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 attributes of all nodes are available for model training and then makes fair predictions. In practice, however, the attributes of some nodes might not be accessible due to missing data or privacy concerns, which makes fair graph learning even more challenging. In this paper, we propose FairAC, a fair attribute completion method, to complement missing information and learn fair node embeddings for graphs with missing attributes. FairAC adopts an attention mechanism to deal with the attribute missing problem and meanwhile, it mitigates two types of unfairness, i.e., feature unfairness from attributes and topological unfairness due to attribute completion. FairAC can work on various types of homogeneous graphs and generate fair embeddings for them and thus can be applied to most downstream tasks to improve their fairness performance. To our best knowledge, FairAC is the first method that jointly addresses the graph attribution completion and graph unfairness problems. Experimental results on benchmark datasets show that our method achieves better fairness performance with less sacrifice in accuracy, compared with the state-of-the-art methods of fair graph learning. Code is available at: https://github.com/donglgcn/FairAC.

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。

↑