Abstract
Beyond improving trust and validating model fairness, xAI practices also have the potential to recover valuable scientific insights in application domains where little to no prior human intuition exists. To that end, we propose a method to extract global concept explanations from the predictions of graph neural networks to develop a deeper understanding of the tasks underlying structure-property relationships. We identify concept explanations as dense clusters in the self-explaining Megan models subgraph latent space. For each concept, we optimize a representative prototype graph and optionally use GPT-4 to provide hypotheses about why each structure has a certain effect on the prediction. We conduct computational experiments on synthetic and real-world graph property prediction tasks. For the synthetic tasks we find that our method correctly reproduces the structural rules by which they were created. For real-world molecular property regression and classification tasks, we find that our method rediscovers established rules of thumb. More specifically, our results for molecular mutagenicity prediction indicate more fine-grained resolution of structural details than existing explainability methods, consistent with previous results from chemistry literature. Overall, our results show promising capability to extract the underlying structure-property relationships for complex graph property prediction tasks.
Abstract (translated)
除了提高信任度和验证模型的公平性外，基于AI的研究还有可能在缺乏先前人类直觉的应用领域中恢复有价值的科学见解。为此，我们提出了一种从图神经网络的预测中提取全局概念解释的方法，以更深入地理解支撑任务结构与属性之间关系的任务结构。我们将概念解释确定为自解释Megan模型的子图潜在空间中的密集聚类。对于每个概念，我们优化一个具有代表性的图，并可选地使用GPT-4来提供关于每个结构对预测的影响的假设。我们在合成和现实世界的图属性预测任务上进行计算实验。对于合成任务，我们发现我们的方法正确地复制了它们创建的结构规则。对于现实世界的分子属性回归和分类任务，我们发现我们的方法重新发现了已有的经验法则。具体来说，我们的分子突变预测结果表明，我们的方法比现有的解释性方法具有更细粒度的结构细节的分辨率，这与化学文献中的 previous results 相一致。总体而言，我们的结果表明，基于AI的研究具有从复杂图属性预测任务中提取底层结构与属性之间关系的有前景的能力。
URL
https://arxiv.org/abs/2404.16532
