Graph Neural Networks (GNNs) have demonstrated remarkable performance across a range of applications involving graph-structured data, particularly in high-stakes domains. However, the opaque nature of their decision-making processes limits their trustworthiness and broader adoption. Existing post-hoc explanation methods aim to improve explainability by identifying subgraphs that influence GNN predictions and adopt mixup strategies to alleviate the out-of-distribution (OOD) issue caused by using subgraphs for prediction. Yet, these approaches typically rely on soft masks, which are inherently unable to fully eliminate label-irrelevant information, allowing redundant structures to leak into the mixup process and hindering the resolution of the OOD problem, thereby degrading explanation fidelity. In this work, we propose HPME, a Hard-Perturbation Mixup Explanation framework grounded in a generalized Graph Information Bottleneck, which leverages graph pooling to extract discrete explanatory subgraphs and to yield an information-capacity bound to thoroughly compress label-irrelevant components. Furthermore, we introduce a novel mixup strategy built upon structure-level replacement, generating in-distribution explanations to effectively mitigate the distribution shift. Extensive experiments on diverse tasks demonstrate that HPME achieves state-of-the-art performance in generating robust and interpretable explanations across both synthetic and real-world datasets.

翻译：图神经网络（GNNs）在涉及图结构数据的多个应用领域（特别是高风险领域）中展现了卓越性能。然而，其决策过程的黑箱特性限制了可信度与广泛采纳。现有的事后解释方法通过识别影响GNN预测的子图来提升可解释性，并采用混合策略缓解因使用子图预测导致的分布外（OOD）问题。然而，这些方法通常依赖软掩码，其本质缺陷在于无法完全消除标签无关信息，导致冗余结构泄露至混合过程，阻碍OOD问题的解决，进而损害解释保真度。本文提出HPME——一种基于广义图信息瓶颈理论的硬扰动混合解释框架，通过图池化提取离散解释子图，并构建信息容量边界以彻底压缩标签无关分量。此外，我们引入基于结构级替换的新型混合策略，生成分布内解释以有效缓解分布偏移。跨多任务的广泛实验表明，HPME在合成与真实数据集上生成鲁棒且可解释的解释时均达到了最先进性能。