On Structural Explanation of Bias in Graph Neural Networks
On Structural Explanation of Bias in Graph Neural Networks
复制标题
DOI：
10.1145/3534678.3539319
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Yushun Dong;Song Wang;Yu Wang;Tyler Derr;Jundong Li
中科院分区：
文献类型：
--
作者：
Yushun Dong;Song Wang;Yu Wang;Tyler Derr;Jundong Li
图神经网络(GNN)在各种图分析问题中表现出了令人满意的性能。因此，它们已成为各种决策场景中事实上的解决方案。然而，GNN可能会产生对某些人口亚群有偏见的结果。最近的一些工作经验表明，输入网络的偏向结构是GNN偏向的一个重要来源。然而，没有研究系统地仔细研究输入网络结构的哪一部分导致对任何给定节点的偏向预测。关于投入网络结构如何影响国民总收入结果偏向的低透明度，在很大程度上限制了国民总收入在各种关键决策情景中的安全采用。在本文中，我们研究了GNN中偏向的结构解释的一个新的研究问题。具体地说，我们提出了一种新的后自组织解释框架来识别两个边集，这两个边集分别能够最大限度地解释任何给定节点的偏差和对GNN预测的公平水平做出最大贡献。这些解释不仅可以全面理解GNN预测的偏差/公平性，而且对于构建一个有效而公平的GNN模型也具有现实意义。在真实世界数据集上的广泛实验验证了所提出的框架在为GNN的偏差提供有效的结构性解释方面的有效性。开放源代码可在https://github.com/yushundong/REFEREE.上找到
Graph Neural Networks (GNNs) have shown satisfying performance in various graph analytical problems. Hence, they have become the de facto solution in a variety of decision-making scenarios. However, GNNs could yield biased results against certain demographic subgroups. Some recent works have empirically shown that the biased structure of the input network is a significant source of bias for GNNs. Nevertheless, no studies have systematically scrutinized which part of the input network structure leads to biased predictions for any given node. The low transparency on how the structure of the input network influences the bias in GNN outcome largely limits the safe adoption of GNNs in various decision-critical scenarios. In this paper, we study a novel research problem of structural explanation of bias in GNNs. Specifically, we propose a novel post-hoc explanation framework to identify two edge sets that can maximally account for the exhibited bias and maximally contribute to the fairness level of the GNN prediction for any given node, respectively. Such explanations not only provide a comprehensive understanding of bias/fairness of GNN predictions but also have practical significance in building an effective yet fair GNN model. Extensive experiments on real-world datasets validate the effectiveness of the proposed framework towards delivering effective structural explanations for the bias of GNNs. Open-source code can be found at https://github.com/yushundong/REFEREE.