Graph learning models achieve state-of-the-art performance on many tasks, but this often requires increasingly large model sizes. Accordingly, the complexity of their representations increase. Explainability techniques (XAI) have made remarkable progress in the interpretability of ML models. However, the non-relational nature of Graph Neural Networks (GNNs) make it difficult to reuse already existing XAI methods. While other works have focused on instance-based explanation methods for GNNs, very few have investigated model-based methods and, to our knowledge, none have tried to probe the embedding of the GNNs for well-known structural graph properties. In this paper we present a model agnostic explainability pipeline for Graph Neural Networks (GNNs) employing diagnostic classifiers. This pipeline aims to probe and interpret the learned representations in GNNs across various architectures and datasets, refining our understanding and trust in these models.

翻译：图学习模型在许多任务上实现了最先进的性能，但这通常需要越来越大的模型规模。相应地，其表示的复杂性也随之增加。可解释性技术（XAI）在机器学习模型的可解释性方面取得了显著进展。然而，图神经网络（GNNs）的非关系特性使得重用现有的XAI方法变得困难。虽然其他研究专注于GNNs的实例级解释方法，但很少有工作探究模型级解释方法，并且据我们所知，尚未有研究尝试从GNNs的嵌入中探测已知的结构图属性。本文提出了一种采用诊断分类器的、与模型无关的图神经网络（GNNs）可解释性流程。该流程旨在探测和解释不同架构与数据集下GNNs学习到的表示，从而深化我们对这些模型的理解与信任。