博弈论视角下的图神经网络反事实解释
Game-theoretic Counterfactual Explanation for Graph Neural Networks
AI总结：
本文提出一种基于半值（Banzhaf值）的非学习反事实解释方法，用于图神经网络节点分类，无需额外训练，较Shapley值方法样本复杂度更低、速度提升达四倍，且在噪声环境下更具鲁棒性，同时保持解释质量。
摘要：
图神经网络（GNNs）已成为复杂网络中节点分类任务的强大工具。然而，其决策过程对用户而言仍是一个黑箱，使得理解其预测背后的推理变得具有挑战性。反事实解释（CFE）在增强机器学习模型的可解释性方面已显示出潜力。以往为GNN计算CFE的方法通常是基于学习的方法，需要训练额外的图。在本文中，我们提出了一种基于半值（semivalue）的非学习方法，用于为节点分类任务生成CFE，从而消除了任何额外训练的需求。我们的结果表明，与其他流行方法（如计算Shapley值）相比，计算Banzhaf值在识别反事实解释时所需的样本复杂度更低。我们的实证证据表明，与Shapley值相比，计算Banzhaf值可实现高达四倍的加速。我们还设计了一种用于计算Banzhaf值的阈值化方法，并展示了其在噪声环境中鲁棒性的理论和实证结果，使其优于Shapley值。此外，在三个流行的图数据集上，阈值化的Banzhaf值被证明能在不损害解释质量（即保真度）的情况下提高效率。
英文摘要：
Graph Neural Networks (GNNs) have been a powerful tool for node classification tasks in complex networks. However, their decision-making processes remain a black-box to users, making it challenging to understand the reasoning behind their predictions. Counterfactual explanations (CFE) have shown promise in enhancing the interpretability of machine learning models. Prior approaches to compute CFE for GNNS often are learning-based approaches that require training additional graphs. In this paper, we propose a semivalue-based, non-learning approach to generate CFE for node classification tasks, eliminating the need for any additional training. Our results reveals that computing Banzhaf values requires lower sample complexity in identifying the counterfactual explanations compared to other popular methods such as computing Shapley values. Our empirical evidence indicates computing Banzhaf values can achieve up to a fourfold speed up compared to Shapley values. We also design a thresholding method for computing Banzhaf values and show theoretical and empirical results on its robustness in noisy environments, making it superior to Shapley values. Furthermore, the thresholded Banzhaf values are shown to enhance efficiency without compromising the quality (i.e., fidelity) in the explanations in three popular graph 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。
