In this work, we propose a methodology for investigating the use of semantic attention to enhance the explainability of Graph Neural Network (GNN)-based models. Graph Deep Learning (GDL) has emerged as a promising field for tasks like scene interpretation, leveraging flexible graph structures to concisely describe complex features and relationships. As traditional explainability methods used in eXplainable AI (XAI) cannot be directly applied to such structures, graph-specific approaches are introduced. Attention has been previously employed to estimate the importance of input features in GDL, however, the fidelity of this method in generating accurate and consistent explanations has been questioned. To evaluate the validity of using attention weights as feature importance indicators, we introduce semantically-informed perturbations and correlate predicted attention weights with the accuracy of the model. Our work extends existing attention-based graph explainability methods by analysing the divergence in the attention distributions in relation to semantically sorted feature sets and the behaviour of a GNN model, efficiently estimating feature importance. We apply our methodology on a lidar pointcloud estimation model successfully identifying key semantic classes that contribute to enhanced performance, effectively generating reliable post-hoc semantic explanations.

翻译：本文提出了一种研究方法，旨在探索利用语义注意力增强基于图神经网络（GNN）模型的可解释性。图深度学习（GDL）已成为场景理解等任务中极具前景的领域，通过灵活的图结构简洁地描述复杂特征与关系。由于可解释人工智能（XAI）中传统解释方法无法直接应用于此类结构，因此引入了图专用的解释方法。尽管注意力机制此前已被用于估计GDL中输入特征的重要性，但其在生成准确且一致的解释方面的保真度仍存疑。为验证将注意力权重作为特征重要性指标的有效性，我们引入了基于语义信息的扰动，并将预测的注意力权重与模型精度相关联。通过分析注意力分布在语义排序特征集上的差异及其与GNN模型行为的关系，本研究扩展了现有基于注意力的图解释方法，高效地估计了特征重要性。我们将该方法应用于激光雷达点云估计模型，成功识别出对提升性能有贡献的关键语义类别，并有效生成了可靠的事后语义解释。