In recent years, attention mechanisms have demonstrated significant potential in the field of graph representation learning. However, while variants of attention-based GNNs are setting new benchmarks for numerous real-world datasets, recent works have pointed out that their induced attentions are less robust and generalizable against noisy graphs due to the lack of direct supervision. In this paper, we present a new framework that utilizes the tool of causality to provide a powerful supervision signal for the learning process of attention functions. Specifically, we estimate the direct causal effect of attention on the final prediction and then maximize such effect to guide attention to attend to more meaningful neighbors. Our method can serve as a plug-and-play module for any canonical attention-based GNNs in an end-to-end fashion. Extensive experiments on a wide range of benchmark datasets illustrated that, by directly supervising attention with our method, the model is able to converge faster with a clearer decision boundary, and thus yields better performances.

翻译：近年来，注意力机制在图表示学习领域展现出显著潜力。然而，尽管基于注意力的图神经网络变体在众多真实数据集上不断刷新基准性能，近期研究指出，这些模型因缺乏直接监督，在含噪图数据上表现出较弱的鲁棒性和泛化能力。本文提出一种新颖框架，利用因果工具为注意力函数的学习过程提供强效监督信号。具体而言，我们估计注意力对最终预测的直接因果效应，并通过最大化该效应来引导注意力聚焦于更具意义的邻居节点。该方法可作为即插即用模块，以端到端方式集成到任意经典基于注意力的图神经网络中。在广泛基准数据集上的大量实验表明，通过采用本方法对注意力进行直接监督，模型能够以更清晰的决策边界更快收敛，从而获得更优性能。