AI 中文总结
提出一种多指标偏好选择方法，通过控制保真度、可解释性和稳定性之间的权衡来生成GNN解释，在多个数据集上优于基线，并能利用模体库提升解释质量。
AI 中文摘要
生成图神经网络（GNN）解释的机制对于建立信任和减轻图神经网络中的偏见至关重要，尤其是在高风险场景中。当前大多数方法仅在稀疏性约束下优化保真度。然而，这忽视了可解释解释（由熟悉的模体模式组成）和稳定解释（在结构扰动下保持不变）的需求。我们提出了一种新颖的方法，在这些指标上优化GNN解释，并将其相对权重作为控制项暴露出来。在包括MUTAG、BA-2Motif、BAMultiShapes和PROTEINS在内的多个真实世界数据集上的实验表明，我们的方法在MUTAG和PROTEINS上所有评估预算下，以及在BA-2Motif上较大预算下，相比最先进的基线产生了更高保真度的解释，同时在较小解释预算范围内速度更快。我们还探讨了，在给定包含相应领域标准模体的输入模体库的情况下，该方法如何用于确定这些模体在生成解释中的相对重要性，以及如何利用这些信息进一步提高输出解释的质量。我们还通过它们引发的权衡曲面检查了不同指标之间的关系，并探讨了其对模体库性质的依赖性。
英文摘要
Mechanisms for generating GNN explanations are crucial for building trust and mitigating biases in Graph Neural Networks (GNNs), especially in high-stakes scenarios. Most current methods optimize only for fidelity under the sparsity constraint. However, this discounts the need for interpretable explanations (those that consist of familiar motif patterns) and stable explanations (those that remain unchanged under structural perturbations). We propose a novel approach that optimizes GNN explanations across these metrics, exposing their relative weighing as a control. Experiments on various real-world datasets, including MUTAG, BA-2Motif, BAMultiShapes, and PROTEINS, suggest that our method produces higher-fidelity explanations than a state-of-the-art baseline on MUTAG and PROTEINS across all evaluated budgets, and on BA-2Motif at larger budgets, while being faster in the regime of small explanation budgets. We also explore how, given an input motif library containing standard motifs for the corresponding domain, the method can be used to determine the relative importance of those motifs in generating the explanations, and how this information can be used to further improve the quality of the output explanations. We also examine the relationship between different metrics through their induced tradeoff surface, and explore its dependence on the nature of the motif library.
