{"ID":3084884,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T05:32:54.120957816Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05756","arxiv_id":"2606.05756","title":"Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability","abstract":"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.","short_abstract":"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 method...","url_abs":"https://arxiv.org/abs/2606.05756","url_pdf":"https://arxiv.org/pdf/2606.05756v1","authors":"[\"Jialiang Yin\",\"Zheng Zhao\",\"Linsey Pang\",\"Bo Dong\",\"Bin Shi\",\"Jiaxing Zhang\"]","published":"2026-06-04T06:32:02Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.IT\"]","methods":"[\"Graph Neural Network\"]","has_code":false}